© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11755
    Prev
    Next
    INDEX
    Explanations

    programming-related definitions and declarations, particularly in header files

    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
    397
    +0.25
    1.5%
    78
    +0.25
    1.5%
    444
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.25
    0.07
    78
    +0.25
    0.02
    9
    +0.13
    0.06
    Negative Logits
    ,'"
    -2.36
    ',
    -2.13
    '),
    -2.08
    '):
    -2.08
    )',
    -2.07
    .',
    -2.05
    ,’
    -2.02
    .",
    -2.00
    ,'
    -1.96
    .'"
    -1.87
    POSITIVE LOGITS
    ª
    4.56
    4.51
    ↵
    4.51
    ↵↵↵
    4.51
    ↵
    4.51
    4.51
    ↵
    4.51
    ↵
    4.51
    4.51
    <|outofrange|>
    4.51
    Activations Density 0.334%

    No Known Activations