© 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. 10340
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Inter" 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
    483
    +0.13
    0.7%
    112
    +0.11
    0.6%
    209
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    483
    +0.13
    0.03
    393
    +0.11
    0.01
    351
    +0.11
    0.03
    Negative Logits
    ering
    -2.05
    ered
    -1.79
    ets
    -1.64
    erate
    -1.64
    ened
    -1.62
    ers
    -1.60
    gery
    -1.59
    erman
    -1.56
    elt
    -1.56
    yer
    -1.53
    POSITIVE LOGITS
    mediate
    2.30
    stitial
    2.24
    actions
    1.80
    pre
    1.76
    facing
    1.74
    medi
    1.72
     alia
    1.72
    stellar
    1.71
    section
    1.69
    sects
    1.68
    Activations Density 0.046%

    No Known Activations