© 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. 11-RES-JB
    11. 4117
    Prev
    Next
    INDEX
    Explanations

    the name "Su"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or entity named "Su."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Triumph
    -0.66
     juggling
    -0.63
     Oblivion
    -0.61
     amplified
    -0.59
     slowing
    -0.59
     Measure
    -0.59
     union
    -0.59
     Normandy
    -0.59
    advertisement
    -0.59
     technicians
    -0.58
    POSITIVE LOGITS
    icidal
    1.37
    icides
    1.34
    zanne
    1.31
    arez
    1.23
    icide
    1.17
    itable
    1.14
    zy
    1.11
    cc
    1.11
    itably
    1.10
    pper
    1.09
    Activations Density 0.011%

    No Known Activations