© 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. 27993
    Prev
    Next
    INDEX
    Explanations

    terms related to science and health

    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
    509
    +0.13
    0.7%
    8
    +0.13
    0.7%
    271
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.13
    0.02
    509
    +0.13
    0.03
    271
    +0.11
    0.00
    Negative Logits
    ĻĤ
    -1.73
    iless
    -1.62
     simultaneously
    -1.62
    inely
    -1.59
    enig
    -1.56
     mistaken
    -1.56
     natural
    -1.53
     clicking
    -1.53
     sexes
    -1.52
     forth
    -1.51
    POSITIVE LOGITS
    fare
    2.13
    sheet
    1.99
    istry
    1.92
    heets
    1.88
    ifact
    1.83
     Committee
    1.83
    helf
    1.76
    place
    1.76
    ivo
    1.75
    iva
    1.72
    Activations Density 0.117%

    No Known Activations