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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 27020
    Prev
    Next
    INDEX
    Explanations

    specific sequences of words and their context within a narrative

    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
    23
    +0.33
    1.9%
    156
    +0.13
    0.8%
    1
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.33
    0.11
    488
    +0.13
    0.06
    56
    +0.12
    -0.01
    Negative Logits
    jsfiddle
    -2.08
    watson
    -2.04
    à±ģ
    -1.89
    àµį
    -1.75
    dimen
    -1.71
    à±į
    -1.65
    pad
    -1.63
    à±
    -1.54
    ées
    -1.54
    coin
    -1.52
    POSITIVE LOGITS
     revealed
    1.92
     unsuccessful
    1.72
     disastrous
    1.67
     later
    1.66
     revealing
    1.66
     subsequent
    1.65
     prompted
    1.62
     children
    1.61
     soon
    1.60
     fate
    1.60
    Activations Density 1.144%

    No Known Activations