© 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. 24723
    Prev
    Next
    INDEX
    Explanations

    occurrences of a specific term related to application programming

    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
    128
    +0.12
    0.7%
    164
    +0.11
    0.6%
    487
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.12
    0.02
    487
    +0.11
    0.02
    164
    +0.10
    0.02
    Negative Logits
    Ĥ
    -2.42
    ķ
    -2.40
    Ń
    -2.38
    ¿½
    -2.23
    Īĺ
    -2.20
    ĵ
    -2.10
    ¼
    -2.07
    Ļª
    -2.00
    ĸ´
    -1.96
    Ĺ
    -1.86
    POSITIVE LOGITS
    unov
    1.97
    orte
    1.93
    holder
    1.63
    witz
    1.63
     Films
    1.59
    itals
    1.59
    shots
    1.57
    hael
    1.56
    enem
    1.55
    icture
    1.54
    Activations Density 0.079%

    No Known Activations