© 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. 30456
    Prev
    Next
    INDEX
    Explanations

    quotation marks or dialogue indicators

    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
    275
    +0.14
    0.8%
    371
    +0.13
    0.7%
    317
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.12
    147
    +0.13
    0.12
    151
    +0.13
    0.13
    Negative Logits
    ľĵ
    -3.54
    £
    -3.16
    Ĵ
    -3.06
    ĥ½
    -3.06
    ĵ
    -3.05
    ĻĤ
    -3.05
    °
    -2.98
    Ń
    -2.97
    «
    -2.87
    ħ
    -2.84
    POSITIVE LOGITS
    ág
    1.69
    áv
    1.67
    '];
    1.62
    itar
    1.52
    tera
    1.50
    .',
    1.47
    ']);
    1.46
    "];
    1.46
    isha
    1.45
     same
    1.44
    Activations Density 3.315%

    No Known Activations