© 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. 30664
    Prev
    Next
    INDEX
    Explanations

    instances of the word "surf" or related terms referencing surfing activities

    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
    115
    +0.12
    0.7%
    256
    +0.11
    0.6%
    46
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.12
    0.01
    46
    +0.11
    0.01
    256
    +0.11
    0.01
    Negative Logits
     sexes
    -1.67
    TY
    -1.43
    ocular
    -1.42
    phe
    -1.41
    inib
    -1.41
    tw
    -1.40
     \:
    -1.39
     où
    -1.35
    ':'
    -1.31
     thumbs
    -1.30
    POSITIVE LOGITS
    etto
    1.74
     legend
    1.73
    notes
    1.68
    able
    1.65
     legends
    1.61
    icro
    1.53
    ings
    1.49
    onent
    1.49
    ably
    1.47
    enos
    1.42
    Activations Density 0.009%

    No Known Activations