© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 11646
    Prev
    Next
    INDEX
    Explanations

    verbs related to struggling with challenges or problems

    oai_token-act-pair · gpt-3.5-turbo

    expressions of struggle or grappling with difficulties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescence
    -0.74
     Cf
    -0.73
    ospons
    -0.69
    vertisement
    -0.69
    rites
    -0.68
    vantage
    -0.66
    markets
    -0.66
    saf
    -0.63
    orig
    -0.63
    added
    -0.63
    POSITIVE LOGITS
     grief
    1.10
     realization
    0.99
     unresolved
    0.98
     guilt
    0.97
     loneliness
    0.96
     reconcil
    0.95
     coping
    0.94
     existential
    0.94
     cope
    0.92
     reconcile
    0.91
    Activations Density 0.555%

    No Known Activations