© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 11383
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and emotional struggles

    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
    186
    +0.28
    1.6%
    56
    +0.15
    0.9%
    156
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.28
    0.23
    156
    +0.15
    0.26
    71
    +0.15
    0.23
    Negative Logits
    forth
    -1.73
    Inflater
    -1.52
    onents
    -1.48
    serialize
    -1.47
    >();
    -1.46
    semb
    -1.46
    ischer
    -1.42
     :=
    -1.41
    $]{};
    -1.40
     result
    -1.39
    POSITIVE LOGITS
    »¿
    1.76
     whom
    1.54
     or
    1.47
    oj
    1.43
     yards
    1.38
     whistle
    1.37
     university
    1.35
    rug
    1.35
     Photograph
    1.33
     disclose
    1.30
    Activations Density 4.858%

    No Known Activations