© 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. 25398
    Prev
    Next
    INDEX
    Explanations

    dates formatted in a specific style

    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
    283
    +0.11
    0.6%
    406
    +0.11
    0.6%
    71
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.11
    0.04
    216
    +0.11
    0.04
    163
    +0.11
    0.03
    Negative Logits
    ī
    -2.25
    ®
    -2.19
    ´
    -2.15
    ↵
    -2.13
    ↵↵
    -2.13
    ↵↵
    -2.13
                  ↵
    -2.13
    -2.13
    <|outofrange|>
    -2.13
    -2.13
    POSITIVE LOGITS
    gered
    1.87
    dered
    1.80
    nbsp
    1.78
    mered
    1.71
    ingly
    1.65
    anted
    1.64
    lies
    1.60
    END
    1.59
    ensable
    1.56
    undred
    1.55
    Activations Density 0.079%

    No Known Activations