© 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. 24981
    Prev
    Next
    INDEX
    Explanations

    technical terms and markup language elements related to coding or software documentation

    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
    47
    +0.13
    0.7%
    136
    +0.12
    0.6%
    293
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.13
    0.18
    136
    +0.12
    -0.09
    90
    +0.11
    0.14
    Negative Logits
    ľĵ
    -2.40
    Ĥ¬
    -2.30
    ĻĤ
    -2.27
    IJ
    -2.18
    Ī
    -2.18
    Ĥ
    -2.18
    ĥ½
    -2.17
    Ŀ
    -2.16
    «
    -2.13
    İ
    -2.09
    POSITIVE LOGITS
    manship
    1.66
    ault
    1.62
    icals
    1.57
    ius
    1.52
    omed
    1.50
    ists
    1.47
    ETHOD
    1.45
     Either
    1.44
    ISM
    1.40
    Ibid
    1.39
    Activations Density 6.869%

    No Known Activations