© 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. 4-RES-SM
    11. 13277
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "adrenaline" and related terms or phrases

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.20
    1.2%
    78
    +0.13
    0.8%
    134
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.20
    0.02
    21
    +0.13
    0.01
    470
    +0.12
    0.01
    Negative Logits
    abouts
    -1.46
     mind
    -1.42
     minds
    -1.40
    ks
    -1.37
     citations
    -1.35
     conclusions
    -1.35
     guide
    -1.34
     Things
    -1.33
     success
    -1.32
     dice
    -1.29
    POSITIVE LOGITS
    ħ
    3.25
    aline
    3.13
    Ħ
    3.12
    ergic
    3.03
    Ļ
    3.02
    Ģ
    2.96
    Ī
    2.90
    ¨
    2.87
    §
    2.86
    ĥ
    2.85
    Activations Density 0.045%

    No Known Activations