© 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. 13298
    Prev
    Next
    INDEX
    Explanations

    code constructs and programming language syntax elements

    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
    78
    +0.23
    1.3%
    263
    +0.14
    0.8%
    225
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.23
    0.01
    57
    +0.14
    0.09
    397
    +0.14
    0.06
    Negative Logits
     ‘
    -3.19
    âĢŁ
    -2.96
    ‘
    -2.70
    ,--
    -2.62
     âĢŀ
    -2.62
    ,”
    -2.49
    ”,
    -2.47
    ?”
    -2.46
     ”
    -2.46
    ,’
    -2.45
    POSITIVE LOGITS
    č↵
    5.67
    č
    5.37
    č↵č↵
    5.25
    č↵
    4.67
    č↵č
    4.66
     č
    4.59
    č↵č↵č
    4.44
    č↵
    4.36
    ^[@
    4.21
    č↵
    4.16
    Activations Density 1.071%

    No Known Activations