Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11903
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    200
    +0.12
    0.7%
    373
    +0.11
    0.6%
    325
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.12
    0.00
    1
    -0.11
    0.00
    2
    -0.11
    0.00
    Negative Logits
    atile
    -1.54
    othetical
    -1.51
    ¨
    -1.50
     unity
    -1.49
    ubuntu
    -1.43
    ||
    -1.42
    arly
    -1.39
    itage
    -1.38
    *=
    -1.35
     analyst
    -1.33
    POSITIVE LOGITS
    iley
    1.70
     chase
    1.67
    tees
    1.49
     route
    1.47
    pee
    1.44
    shore
    1.43
     tandem
    1.41
    ientes
    1.39
    ITC
    1.38
    iente
    1.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.