© 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. Residuals
    9. 4-RES-SM
    11. 13399
    Prev
    Next
    INDEX
    Explanations

    license terms and URLs related to software

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    90
    +0.14
    0.8%
    142
    +0.13
    0.7%
    234
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.02
    90
    +0.13
    0.03
    142
    +0.11
    0.01
    Negative Logits
     Calgary
    -1.92
     Fraser
    -1.85
     tumour
    -1.83
     Winnipeg
    -1.81
     Sask
    -1.78
     Montreal
    -1.74
     Ottawa
    -1.74
     Edmonton
    -1.73
    monton
    -1.68
     Baghdad
    -1.67
    POSITIVE LOGITS
     Eclipse
    3.45
     eclipse
    3.23
    clipse
    2.78
    eclipse
    2.73
    maven
    2.03
     JD
    2.00
     ecl
    1.95
     Saturn
    1.86
     jav
    1.84
     Hoover
    1.77
    Activations Density 0.318%

    No Known Activations