© 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. 11693
    Prev
    Next
    INDEX
    Explanations

    structure and assignments in programming or scripting languages

    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
    +0.15
    0.8%
    466
    +0.14
    0.8%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.15
    0.04
    284
    +0.14
    0.04
    405
    +0.12
    0.04
    Negative Logits
    .);
    -1.72
    rected
    -1.60
    umab
    -1.58
    herin
    -1.51
    will
    -1.48
    vity
    -1.44
    romycin
    -1.43
    !");
    -1.41
    PEG
    -1.41
    holds
    -1.40
    POSITIVE LOGITS
    Ļª
    5.23
    5.20
    ↵
    5.20
    5.20
                ↵
    5.20
    5.20
    ↵Č
    5.20
    ↵↵↵
    5.20
    ↵↵
    5.20
    č↵
    5.20
    Activations Density 0.303%

    No Known Activations