© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26061
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software licenses and documentation

    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
    244
    +0.13
    0.7%
    265
    +0.13
    0.7%
    143
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    265
    +0.13
    0.03
    273
    +0.13
    0.01
    95
    +0.12
    0.02
    Negative Logits
    ,...
    -1.56
    tons
    -1.55
     consistency
    -1.49
     emphas
    -1.42
     favour
    -1.42
    ';
    -1.41
    isation
    -1.40
    ..
    -1.39
    ...'
    -1.38
    '.
    -1.35
    POSITIVE LOGITS
    googleapis
    1.72
    ublic
    1.72
    ()));
    1.67
     transcript
    1.67
    ))$,
    1.67
    youtube
    1.62
    ŀ
    1.54
    blogs
    1.53
     Atty
    1.50
    "));
    1.49
    Activations Density 0.240%

    No Known Activations