© 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. 29490
    Prev
    Next
    INDEX
    Explanations

    contradictions and qualifications in statements

    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
    186
    +0.14
    0.8%
    88
    +0.14
    0.8%
    167
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.14
    0.16
    478
    +0.14
    0.01
    167
    +0.14
    0.03
    Negative Logits
    iew
    -1.91
     ai
    -1.44
     transducer
    -1.44
    imedia
    -1.40
    ylate
    -1.36
     acquainted
    -1.36
    ="{
    -1.32
    together
    -1.31
    ître
    -1.31
     together
    -1.29
    POSITIVE LOGITS
    ¼
    2.21
    ©
    2.06
     wrong
    1.94
    ¨
    1.91
    ĺ
    1.86
    Īĺ
    1.83
    ī
    1.83
    1.82
    <|outofrange|>
    1.82
    1.82
    Activations Density 3.663%

    No Known Activations