© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 30755
    Prev
    Next
    INDEX
    Explanations

    programming function definitions and related code structures

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    73
    +0.15
    0.8%
    215
    +0.12
    0.6%
    414
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.15
    0.11
    394
    +0.12
    0.12
    322
    +0.11
    0.11
    Negative Logits
    ĻĤ
    -1.73
    ]\]).
    -1.63
     crap
    -1.63
    \]](
    -1.50
    ~)
    -1.49
    >).
    -1.49
    ¢
    -1.46
    cycl
    -1.44
    ~).
    -1.42
     KD
    -1.42
    POSITIVE LOGITS
    yon
    1.70
    ringe
    1.57
    raud
    1.54
    olite
    1.52
     biography
    1.51
     shed
    1.50
    okin
    1.46
     locality
    1.44
    ameter
    1.38
     mart
    1.37
    Activations Density 0.266%

    No Known Activations