© 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 EvalsExportsinterp-engineNEWAPI 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. 28180
    Prev
    Next
    INDEX
    Explanations

    the presence and usage of the term "sender."

    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
    376
    +0.11
    0.6%
    271
    +0.11
    0.6%
    184
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.11
    0.02
    73
    +0.11
    0.01
    94
    +0.10
    0.01
    Negative Logits
     scholars
    -1.60
     Kingdom
    -1.55
    alus
    -1.42
    ...](
    -1.41
     scholarship
    -1.40
    Ethics
    -1.36
     meaning
    -1.35
     National
    -1.33
     Respondent
    -1.33
    itarian
    -1.32
    POSITIVE LOGITS
    áŁ
    1.86
    à§
    1.85
    ા
    1.84
    র
    1.81
    à§į
    1.75
    àµį
    1.70
    à«
    1.66
    Īĺ
    1.65
    àµ
    1.63
    ение
    1.63
    Activations Density 0.080%

    No Known Activations