© 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. 26908
    Prev
    Next
    INDEX
    Explanations

    numerical thresholds in various 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/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
    108
    +0.14
    0.8%
    246
    +0.12
    0.7%
    307
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.14
    0.01
    334
    +0.12
    0.01
    381
    +0.12
    0.01
    Negative Logits
    Ī
    -1.89
    ¤
    -1.82
    pite
    -1.72
    ĵ
    -1.67
    ľ
    -1.62
    ·¸
    -1.60
    ¬
    -1.57
    ANS
    -1.56
    LLOW
    -1.54
    hs
    -1.53
    POSITIVE LOGITS
    ÃŃvel
    2.00
    erior
    1.70
    rá
    1.69
    krit
    1.66
    forum
    1.65
    dit
    1.65
     tier
    1.63
    abad
    1.58
    lane
    1.56
    liga
    1.53
    Activations Density 0.064%

    No Known Activations