© 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. 27758
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used for separation or emphasis

    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
    23
    +0.45
    2.8%
    478
    +0.17
    1.1%
    203
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.45
    0.14
    203
    +0.17
    0.12
    488
    +0.12
    0.10
    Negative Logits
    ¾
    -1.78
    ,
    -1.78
    ford
    -1.69
    iano
    -1.68
    Īĺ
    -1.68
    room
    -1.68
    ÅĽci
    -1.67
    etto
    -1.66
    hart
    -1.65
    pad
    -1.64
    POSITIVE LOGITS
     blame
    2.19
     sudden
    1.93
      ↵
    1.89
     fate
    1.79
     say
    1.71
    '));
    1.69
     slightest
    1.65
     children
    1.64
     babies
    1.63
    rapy
    1.62
    Activations Density 1.363%

    No Known Activations