© 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. 26240
    Prev
    Next
    INDEX
    Explanations

    words related to color codes or visual elements in design

    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
    12
    +0.11
    0.6%
    369
    +0.10
    0.6%
    313
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.11
    0.03
    162
    +0.10
    0.03
    296
    +0.10
    0.03
    Negative Logits
     myself
    -1.60
     sudden
    -1.59
    unreadable
    -1.48
    cluding
    -1.48
     truth
    -1.46
     disbelief
    -1.42
    cha
    -1.37
     dressed
    -1.36
    cess
    -1.35
     urgent
    -1.35
    POSITIVE LOGITS
    OUBLE
    2.17
    ictionary
    2.03
    ynamic
    1.99
    resse
    1.95
    Gs
    1.88
    GE
    1.78
    MSO
    1.76
    ress
    1.71
    VERTIS
    1.71
    isease
    1.71
    Activations Density 0.143%

    No Known Activations