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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27787
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "I" to identify personal reflections or experiences

    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
    +0.22
    1.3%
    369
    +0.15
    0.9%
    478
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.22
    0.03
    85
    +0.15
    0.03
    351
    +0.13
    0.03
    Negative Logits
    »¿
    -2.51
    ĨĴ
    -2.44
    ¼
    -2.36
    ↵
    -2.25
    ↵
    -2.25
    <|outofrange|>
    -2.25
    -2.25
    ↵
    -2.25
    -2.25
    -2.25
    POSITIVE LOGITS
    nez
    2.26
    stanbul
    1.89
    rr
    1.88
     hereby
    1.78
     secretly
    1.76
    celand
    1.75
    yy
    1.67
    lium
    1.64
    reland
    1.63
     pity
    1.62
    Activations Density 0.130%

    No Known Activations