© 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. 25576
    Prev
    Next
    INDEX
    Explanations

    references to the brain and its functions

    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
    71
    +0.15
    0.9%
    156
    +0.14
    0.8%
    188
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.15
    0.02
    71
    +0.14
    0.02
    146
    +0.13
    0.02
    Negative Logits
    aturday
    -1.61
    sible
    -1.61
    umbent
    -1.60
    ra
    -1.48
    ments
    -1.48
     promise
    -1.45
    ment
    -1.44
    >>>
    -1.44
    estinal
    -1.42
    opropyl
    -1.40
    POSITIVE LOGITS
    stem
    2.16
    storm
    1.92
    scape
    1.90
    works
    1.87
     plays
    1.74
     contributes
    1.74
     correlates
    1.69
    less
    1.67
    FX
    1.65
     mechanisms
    1.61
    Activations Density 0.044%

    No Known Activations