© 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. 29107
    Prev
    Next
    INDEX
    Explanations

    dialogue or speech attribution in the text

    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
    331
    +0.12
    0.7%
    31
    +0.11
    0.6%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    331
    +0.12
    0.08
    269
    +0.11
    0.07
    82
    +0.11
    0.06
    Negative Logits
     favour
    -1.62
     mistaken
    -1.54
    AML
    -1.54
     favoured
    -1.53
     strongest
    -1.39
    ·¸
    -1.36
    vast
    -1.35
    ophobia
    -1.35
     minds
    -1.31
    opin
    -1.30
    POSITIVE LOGITS
    release
    1.44
     )"
    1.41
    card
    1.37
    â
    1.36
     }}
    1.35
    ifice
    1.33
    Ïĥη
    1.31
    xe
    1.28
    ี
    1.28
     insert
    1.25
    Activations Density 2.034%

    No Known Activations