© 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. 28461
    Prev
    Next
    INDEX
    Explanations

    references to oneself or self-identification

    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
    291
    +0.11
    0.6%
    483
    +0.10
    0.6%
    52
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.11
    0.02
    211
    +0.10
    0.02
    198
    +0.10
    0.02
    Negative Logits
    ibr
    -1.75
    lections
    -1.73
    ends
    -1.51
    ille
    -1.47
    bey
    -1.47
    bers
    -1.44
     office
    -1.37
    ents
    -1.37
    ала
    -1.37
    enda
    -1.34
    POSITIVE LOGITS
     predictor
    1.42
    .....
    1.37
     predictors
    1.36
    seys
    1.35
    furt
    1.33
     tob
    1.32
     UT
    1.31
     Federation
    1.30
    uced
    1.28
    uclear
    1.28
    Activations Density 0.006%

    No Known Activations