© 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. 1-RES-SM
    11. 24760
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming elements in the text

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    2
    +0.20
    1.2%
    77
    +0.11
    0.7%
    350
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.20
    0.04
    245
    +0.11
    0.03
    143
    +0.10
    0.02
    Negative Logits
    ¯
    -3.83
    ·¸
    -3.78
    ³
    -3.72
    Ħ
    -3.55
    ł
    -3.39
    £
    -3.35
    Ļª
    -3.32
    ¥
    -3.25
    ľĵ
    -3.21
    ©
    -3.18
    POSITIVE LOGITS
    haus
    2.01
    pec
    1.79
    ÅĽÄĩ
    1.78
    cs
    1.68
    ÃŃf
    1.66
     deals
    1.65
    aho
    1.61
    greg
    1.59
    ball
    1.57
    ÅĽci
    1.56
    Activations Density 0.093%

    No Known Activations