© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24072
    Prev
    Next
    INDEX
    Explanations

    references to self-related concepts or the notion of selfhood

    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
    172
    +0.15
    0.8%
    380
    +0.13
    0.7%
    386
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.15
    0.04
    172
    +0.13
    0.03
    380
    +0.13
    0.03
    Negative Logits
    ubicin
    -1.96
    amycin
    -1.71
    pine
    -1.66
    estion
    -1.61
    th
    -1.58
    hin
    -1.58
    chers
    -1.57
    oslav
    -1.56
     deadly
    -1.52
    paces
    -1.51
    POSITIVE LOGITS
    ¼
    3.44
    Ħ
    2.67
    Īĺ
    2.61
    ³
    2.60
    ¸
    2.59
    ĭ
    2.58
    ±
    2.57
    Ļ
    2.56
    µ
    2.53
    Ł
    2.48
    Activations Density 0.064%

    No Known Activations