© 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. 4-RES-SM
    11. 11214
    Prev
    Next
    INDEX
    Explanations

    references to programming and project identifiers in an API context

    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
    +0.20
    1.2%
    450
    +0.14
    0.9%
    271
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.20
    0.03
    255
    +0.14
    0.00
    203
    +0.12
    0.02
    Negative Logits
     closely
    -1.73
     these
    -1.51
     Athletics
    -1.37
    :--
    -1.34
     terms
    -1.34
    atically
    -1.34
    stant
    -1.33
    hedral
    -1.32
     sexes
    -1.31
    etheless
    -1.29
    POSITIVE LOGITS
    °
    5.03
    ¹
    4.76
    ª
    4.72
    ĥ
    4.68
    ¯
    4.67
    Ģ
    4.57
    ¾
    4.53
    ĨĴ
    4.51
    ©
    4.45
    Ĩ
    4.44
    Activations Density 0.131%

    No Known Activations