© 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. 26698
    Prev
    Next
    INDEX
    Explanations

    references to projects and project-related actions in development contexts

    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
    466
    +0.14
    0.8%
    175
    +0.11
    0.6%
    456
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.14
    0.03
    120
    +0.11
    0.03
    401
    +0.10
    0.03
    Negative Logits
    '?"
    -1.73
    "?
    -1.72
    ?_
    -1.65
    ?"
    -1.63
    _."
    -1.58
    ITION
    -1.55
    igned
    -1.48
    )?
    -1.45
    '?
    -1.41
    "?"
    -1.40
    POSITIVE LOGITS
    zyk
    1.60
    front
    1.57
     mercy
    1.53
    ÃŁe
    1.51
    zig
    1.51
     LLP
    1.48
    jem
    1.47
    procedure
    1.41
    Å¡ÃŃ
    1.39
    ksen
    1.34
    Activations Density 0.179%

    No Known Activations