© 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. 4-RES-SM
    11. 10175
    Prev
    Next
    INDEX
    Explanations

    references to the term "Black" 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    369
    +0.14
    0.8%
    109
    +0.11
    0.6%
    116
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.14
    0.03
    116
    +0.11
    0.03
    124
    +0.11
    0.03
    Negative Logits
    iries
    -1.74
    anson
    -1.72
    usement
    -1.72
    ants
    -1.64
    uristic
    -1.62
    imental
    -1.59
    atically
    -1.57
    antly
    -1.57
    istically
    -1.57
    ontally
    -1.56
    POSITIVE LOGITS
    listed
    2.79
    smith
    2.57
    pool
    2.40
    ened
    2.38
    Berry
    2.30
    listing
    2.27
    list
    2.25
    jack
    2.23
    adder
    2.23
    berry
    2.15
    Activations Density 0.123%

    No Known Activations