© 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. 4-RES-JB
    11. 10757
    Prev
    Next
    INDEX
    Explanations

    references to the superhero "Captain America"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Captain America

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

    No Comments

    Negative Logits
    td
    -0.79
    pher
    -0.75
    entity
    -0.74
    ilateral
    -0.73
    ulous
    -0.71
    itsch
    -0.70
    ":"/
    -0.70
    erg
    -0.70
    elf
    -0.70
    ucl
    -0.69
    POSITIVE LOGITS
     Kidd
    0.98
     Marvel
    0.87
    berries
    0.87
    ĨĴ
    0.86
     Hook
    0.86
    berry
    0.83
     Captain
    0.82
     Falcon
    0.80
     Jack
    0.77
     Reef
    0.77
    Activations Density 0.010%

    No Known Activations