© 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. 30366
    Prev
    Next
    INDEX
    Explanations

    date formats

    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
    69
    +0.16
    0.9%
    391
    +0.12
    0.7%
    458
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    456
    +0.16
    0.02
    391
    +0.12
    0.02
    69
    +0.12
    0.02
    Negative Logits
    arity
    -1.73
     late
    -1.56
    ?).
    -1.44
     pity
    -1.44
     midst
    -1.43
     ">
    -1.41
    olysis
    -1.37
     absence
    -1.36
    ly
    -1.34
     deaf
    -1.33
    POSITIVE LOGITS
    ª
    3.41
    ³
    3.12
    ĥ½
    3.02
    ¾
    2.94
    ¥
    2.89
    ¿
    2.84
    Ń
    2.81
    į
    2.81
    °
    2.75
    Ľ
    2.74
    Activations Density 0.014%

    No Known Activations