© 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. 10991
    Prev
    Next
    INDEX
    Explanations

    comment blocks or documentation in code

    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
    +0.28
    1.7%
    397
    +0.13
    0.8%
    272
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    272
    +0.28
    0.04
    78
    +0.13
    0.01
    375
    +0.12
    0.03
    Negative Logits
    gage
    -1.53
    rive
    -1.44
    hed
    -1.43
    vist
    -1.43
    dess
    -1.41
    WARE
    -1.40
    ceral
    -1.38
    hold
    -1.38
    ging
    -1.36
    ITED
    -1.35
    POSITIVE LOGITS
    ij
    5.35
    ↵↵↵
    5.29
    ↵Č
    5.29
    ↵↵
    5.29
    <|outofrange|>
    5.29
    5.29
    5.29
    5.29
    ↵↵
    5.29
    č↵
    5.29
    Activations Density 0.143%

    No Known Activations