© 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. 29098
    Prev
    Next
    INDEX
    Explanations

    mentions of advantages and comparisons between options

    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
    123
    +0.13
    0.7%
    166
    +0.12
    0.7%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.13
    0.04
    311
    +0.12
    0.03
    365
    +0.12
    0.03
    Negative Logits
    ¿½
    -3.39
    »
    -2.86
    ¼
    -2.86
    »¿
    -2.73
    ↵
    -2.62
    <|outofrange|>
    -2.62
     ↵
    -2.62
    -2.62
    -2.62
     ↵
    -2.62
    POSITIVE LOGITS
     inherent
    1.65
    ionic
    1.50
    pace
    1.50
    igned
    1.47
    ously
    1.44
    oid
    1.41
    onents
    1.40
     avail
    1.40
    icular
    1.40
     latency
    1.38
    Activations Density 0.221%

    No Known Activations