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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11677
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "an" and the word "the"

    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/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
    74
    +0.13
    0.7%
    222
    +0.12
    0.7%
    98
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.13
    0.02
    74
    +0.12
    0.01
    371
    +0.12
    0.02
    Negative Logits
     headlines
    -1.80
    tig
    -1.74
    Figure
    -1.64
     conversions
    -1.57
     respectively
    -1.53
    cursors
    -1.40
     starters
    -1.40
     medalists
    -1.40
    valence
    -1.36
     fans
    -1.34
    POSITIVE LOGITS
    sible
    1.72
     revoked
    1.65
     blinded
    1.44
     expired
    1.43
     renewal
    1.41
    ·
    1.41
     domain
    1.40
     grant
    1.37
     unrelated
    1.36
     revocation
    1.36
    Activations Density 0.028%

    No Known Activations