© 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. 26372
    Prev
    Next
    INDEX
    Explanations

    references to a linear or direct quality in descriptions

    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
    296
    +0.16
    0.9%
    404
    +0.13
    0.7%
    139
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.16
    0.03
    404
    +0.13
    0.02
    139
    +0.13
    0.02
    Negative Logits
    ¦
    -2.50
    uality
    -2.17
    ľĵ
    -1.79
     Authority
    -1.77
    ¨
    -1.76
    §
    -1.69
    OPE
    -1.68
    ı
    -1.66
    ĵ
    -1.65
    imon
    -1.62
    POSITIVE LOGITS
    eners
    1.90
    lund
    1.81
    ening
    1.70
    ström
    1.66
    eler
    1.66
    FACE
    1.66
    away
    1.52
    edge
    1.52
    genstein
    1.51
    enin
    1.49
    Activations Density 0.096%

    No Known Activations