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. 1-RES-SM
    6. 26772
    Prev
    Next
    INDEX
    Explanations

    references to data structures or computational blocks in programming contexts

    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
    156
    +0.14
    0.8%
    166
    +0.13
    0.8%
    506
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    506
    +0.14
    0.02
    91
    +0.13
    0.03
    166
    +0.12
    0.02
    Negative Logits
    consin
    -1.78
     welcome
    -1.73
    oglobin
    -1.64
     APPEALS
    -1.64
    ICAN
    -1.63
    ICO
    -1.60
    LLOW
    -1.58
    rial
    -1.55
    rious
    -1.52
    tox
    -1.50
    POSITIVE LOGITS
    chains
    2.33
    ÃŃs
    2.10
    quote
    2.04
    ridges
    2.00
    pad
    1.93
    chain
    1.91
    smith
    1.85
    ridge
    1.80
     violates
    1.80
    ings
    1.79
    Activations Density 0.162%

    No Known Activations