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. 26830
    Prev
    Next
    INDEX
    Explanations

    discussion points about patient experiences and perspectives related to illness

    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
    2.0%
    478
    +0.14
    0.8%
    203
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.33
    0.17
    467
    +0.14
    0.11
    23
    +0.13
    0.13
    Negative Logits
    chaft
    -2.08
    ista
    -2.03
    ,
    -1.95
    ings
    -1.94
    ismo
    -1.87
    icles
    -1.82
    ue
    -1.81
    eless
    -1.80
    manship
    -1.79
    EMENT
    -1.79
    POSITIVE LOGITS
     sudden
    1.70
    yet
    1.65
    expand
    1.63
    gently
    1.62
    sed
    1.59
    separated
    1.57
    then
    1.49
    driving
    1.48
    completely
    1.47
    particularly
    1.47
    Activations Density 1.447%

    No Known Activations