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

    Neuronpedia

    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. 26860
    Prev
    Next
    INDEX
    Explanations

    terms related to community assistance and financial support systems

    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
    23
    +0.17
    0.9%
    379
    +0.11
    0.6%
    401
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.17
    0.12
    23
    +0.11
    0.08
    51
    +0.11
    0.12
    Negative Logits
     Plot
    -1.61
     Bulls
    -1.44
    ends
    -1.43
     Tig
    -1.40
    rä
    -1.39
     Ark
    -1.37
     Marathon
    -1.36
     HBO
    -1.36
     Bat
    -1.35
    elines
    -1.33
    POSITIVE LOGITS
     heels
    1.58
    aptic
    1.57
    :`
    1.56
    quo
    1.50
     aged
    1.43
    ,'"
    1.41
    ESULT
    1.40
    '>
    1.40
    .'"
    1.39
     expected
    1.38
    Activations Density 1.200%

    No Known Activations