© 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. 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. 3863
    Prev
    Next
    INDEX
    Explanations

    medical conditions, injuries, and related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "received" and related terms that indicate suffering or experiencing negative conditions

    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
     pasture
    -0.69
     faint
    -0.64
     Boss
    -0.57
    fts
    -0.56
     obscurity
    -0.55
    tein
    -0.55
    herry
    -0.53
     Zamb
    -0.53
     Lit
    -0.53
     leagues
    -0.51
    POSITIVE LOGITS
     during
    0.95
     regarding
    0.90
     throughout
    0.88
     beforehand
    0.81
    igraph
    0.79
     whilst
    0.78
    .:
    0.74
     before
    0.72
    advertisement
    0.71
     while
    0.70
    Activations Density 0.277%

    No Known Activations