© 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 EvalsExportsAPI 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. 26079
    Prev
    Next
    INDEX
    Explanations

    recurring references to "it" in various contexts

    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
    419
    +0.13
    0.7%
    352
    +0.12
    0.6%
    185
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.06
    185
    +0.12
    0.04
    486
    +0.12
    0.05
    Negative Logits
    indo
    -1.61
    erred
    -1.52
    player
    -1.46
    plate
    -1.41
    drawn
    -1.38
     Must
    -1.38
     fashioned
    -1.38
    placeholder
    -1.37
    icularly
    -1.36
    mozilla
    -1.36
    POSITIVE LOGITS
    rier
    1.66
     asleep
    1.65
    ){#
    1.54
    unov
    1.48
    alian
    1.46
     GHz
    1.41
    opause
    1.39
     younger
    1.37
     Collaboration
    1.36
    rey
    1.35
    Activations Density 0.576%

    No Known Activations