© 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. 1-RES-SM
    11. 27434
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of customer service or interpersonal interactions

    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
    156
    +0.20
    1.2%
    29
    +0.11
    0.6%
    252
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.12
    156
    +0.11
    0.07
    271
    +0.10
    0.04
    Negative Logits
    ¸
    -1.74
    ±
    -1.56
    §
    -1.50
    ĨĴ
    -1.50
    rine
    -1.48
    ļ
    -1.48
    »
    -1.46
    ©
    -1.46
    «
    -1.45
     dramatic
    -1.45
    POSITIVE LOGITS
    fony
    2.13
    "}](#
    2.10
    ware
    1.78
    Interface
    1.63
    issance
    1.59
    ircraft
    1.59
    rowser
    1.56
    EV
    1.56
    obile
    1.55
    est
    1.55
    Activations Density 0.443%

    No Known Activations