© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2665
    Prev
    Next
    INDEX
    Explanations

    proper names or names of people

    oai_token-act-pair · gpt-3.5-turbo

    specific pronouns and references to individuals in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seah
    -0.71
     Seat
    -0.70
    hap
    -0.69
    advertisement
    -0.64
    ARA
    -0.61
     Ballard
    -0.61
     halftime
    -0.59
     Palest
    -0.59
    detail
    -0.57
    icative
    -0.57
    POSITIVE LOGITS
     wont
    0.99
    'll
    0.91
     cant
    0.86
     should
    0.86
     didnt
    0.85
     would
    0.82
    izons
    0.81
     could
    0.81
     doesnt
    0.81
     will
    0.81
    Activations Density 0.264%

    No Known Activations