© 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. 28523
    Prev
    Next
    INDEX
    Explanations

    signs of physical struggle or conflict

    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
    56
    +0.19
    1.1%
    320
    +0.11
    0.6%
    69
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.19
    0.12
    56
    +0.11
    -0.02
    320
    +0.11
    0.06
    Negative Logits
    uality
    -1.55
    OURCES
    -1.52
     solely
    -1.45
    éĹ´
    -1.45
    umerable
    -1.45
    ivals
    -1.42
     preferences
    -1.37
    ESSION
    -1.36
     coincides
    -1.35
     resides
    -1.35
    POSITIVE LOGITS
    wagen
    1.72
    eled
    1.61
     retard
    1.52
    escap
    1.45
    kie
    1.44
    ailable
    1.35
     lure
    1.34
     lifeless
    1.33
     aggressive
    1.33
     oz
    1.32
    Activations Density 1.896%

    No Known Activations