© 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. 25370
    Prev
    Next
    INDEX
    Explanations

    the recurring sequence of numbers in a format that indicates significance or reference points

    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
    290
    +0.12
    0.7%
    2
    +0.12
    0.7%
    246
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.12
    0.01
    290
    +0.12
    0.01
    158
    +0.11
    0.01
    Negative Logits
     close
    -1.73
     reversal
    -1.58
     whom
    -1.55
     Channel
    -1.52
     pity
    -1.49
    elian
    -1.48
    eties
    -1.47
     encephal
    -1.46
     whose
    -1.44
     anymore
    -1.43
    POSITIVE LOGITS
    lege
    1.99
    nd
    1.74
    bed
    1.71
    face
    1.70
    assic
    1.70
    enstein
    1.68
    ŀ
    1.66
    icip
    1.64
    fing
    1.61
    veolar
    1.60
    Activations Density 0.011%

    No Known Activations