© 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. 4-RES-SM
    11. 13731
    Prev
    Next
    INDEX
    Explanations

    terms related to stress and its various manifestations

    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
    337
    +0.12
    0.7%
    108
    +0.12
    0.7%
    97
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.12
    0.03
    164
    +0.12
    0.03
    287
    +0.11
    0.03
    Negative Logits
    áĢ¯
    -1.71
     confidential
    -1.62
    poons
    -1.59
     sep
    -1.58
     daylight
    -1.57
    ¿½
    -1.56
    twitter
    -1.55
    lı
    -1.50
    anco
    -1.49
     GNU
    -1.44
    POSITIVE LOGITS
    oria
    2.22
    or
    2.09
     hormones
    2.07
     onset
    1.96
     response
    1.95
     tolerance
    1.95
     occasion
    1.91
     responses
    1.90
     imposed
    1.88
     conditions
    1.86
    Activations Density 0.191%

    No Known Activations