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. 11678
    Prev
    Next
    INDEX
    Explanations

    conditional statements, particularly those involving "if" and "else"

    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
    376
    +0.15
    0.8%
    244
    +0.14
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.15
    0.04
    383
    +0.14
    0.05
    411
    +0.14
    0.04
    Negative Logits
    fully
    -1.53
    ?”
    -1.52
    References
    -1.37
    ERN
    -1.35
    aurus
    -1.35
    VEN
    -1.35
    ERV
    -1.34
    orate
    -1.31
    å¦Ĥ
    -1.28
    anic
    -1.27
    POSITIVE LOGITS
     (!(
    1.71
     (!
    1.62
     INFO
    1.45
     circumstances
    1.45
    (!
    1.39
     conditions
    1.38
     ([
    1.37
     (((
    1.36
    ask
    1.34
    acic
    1.34
    Activations Density 0.146%

    No Known Activations