© 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. 30487
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "av" within various contexts, possibly indicating a focus on audio or visual content

    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
    410
    +0.12
    0.7%
    467
    +0.12
    0.7%
    314
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.12
    0.03
    332
    +0.12
    0.02
    400
    +0.12
    0.02
    Negative Logits
    ·¸
    -1.83
    ĵ
    -1.82
    ľĵ
    -1.77
    Ĥ
    -1.58
    ovanni
    -1.56
    Ļ
    -1.53
    ·
    -1.47
    ķ
    -1.46
    »¿
    -1.46
    ´
    -1.42
    POSITIVE LOGITS
    ailable
    1.93
    enging
    1.60
     holdings
    1.59
    ailability
    1.56
    enstein
    1.56
     patents
    1.54
    witz
    1.53
    codec
    1.52
    sburg
    1.51
    ilion
    1.50
    Activations Density 0.018%

    No Known Activations