© 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. Residuals
    9. 2-RES-SM
    11. 31328
    Prev
    Next
    INDEX
    Explanations

    code files and script-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    350
    +0.14
    0.8%
    157
    +0.13
    0.7%
    93
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.14
    0.06
    250
    +0.13
    0.06
    109
    +0.11
    0.04
    Negative Logits
    Ĭ
    -2.18
    Ĥ¬
    -2.06
    ¿½
    -2.05
    ¬
    -1.96
    ´
    -1.94
     alike
    -1.85
    .]{}
    -1.84
    ķ
    -1.82
    ľĵ
    -1.74
    ħ
    -1.70
    POSITIVE LOGITS
    proj
    1.80
     files
    1.77
     Redistributions
    1.75
    ossier
    1.68
    anked
    1.67
    schema
    1.65
    ctx
    1.64
    #:
    1.57
     file
    1.55
    engine
    1.53
    Activations Density 0.275%

    No Known Activations