© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 24813
    Prev
    Next
    INDEX
    Explanations

    references to ongoing actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    271
    +0.17
    0.9%
    227
    +0.14
    0.8%
    66
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.17
    0.35
    227
    +0.14
    0.36
    473
    +0.13
    0.36
    Negative Logits
    Argued
    -1.48
     vacated
    -1.43
    ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
    -1.42
     dove
    -1.41
     didnt
    -1.40
    ("/
    -1.40
     MW
    -1.39
    ~.
    -1.36
     AdS
    -1.34
     ga
    -1.33
    POSITIVE LOGITS
    ´
    3.87
    Ĩ
    3.67
    ĸ
    3.64
    ¦
    3.58
    ª
    3.55
    «
    3.53
    ł
    3.51
    ĺ
    3.48
    §
    3.44
    ¨
    3.39
    Activations Density 4.397%

    No Known Activations