© 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. 9388
    Prev
    Next
    INDEX
    Explanations

    references to carbohydrates 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
    78
    +0.13
    0.7%
    354
    +0.10
    0.5%
    321
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.13
    0.02
    437
    +0.10
    0.02
    469
    +0.10
    0.01
    Negative Logits
    hin
    -1.77
    thens
    -1.64
    ed
    -1.61
    wards
    -1.58
    abouts
    -1.58
    IBLE
    -1.56
     flock
    -1.53
    er
    -1.50
    soever
    -1.48
    hov
    -1.44
    POSITIVE LOGITS
    Į
    3.66
    Ĩ
    3.52
    µ
    3.20
    ĩ
    3.17
    ļ
    3.13
    §
    3.07
    İ
    3.07
    ı
    3.01
    Ļ
    2.98
    ¯
    2.98
    Activations Density 0.088%

    No Known Activations