© 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 EvalsExportsAPI 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. 28854
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to font sizing and typesetting configurations

    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
    118
    +0.12
    0.7%
    96
    +0.11
    0.6%
    487
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.12
    0.02
    96
    +0.11
    0.03
    192
    +0.11
    0.02
    Negative Logits
     **(
    -1.59
    hip
    -1.59
    ights
    -1.58
     Participants
    -1.57
     Subjects
    -1.57
     colon
    -1.48
     stomach
    -1.47
     between
    -1.46
     SPSS
    -1.46
     longitude
    -1.46
    POSITIVE LOGITS
    inux
    1.79
    punk
    1.70
    illion
    1.65
    onent
    1.64
    tie
    1.63
    orandum
    1.60
    imization
    1.59
    nik
    1.59
    room
    1.58
    ionate
    1.56
    Activations Density 0.019%

    No Known Activations