© 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. 2-RES-JB
    11. 12960
    Prev
    Next
    INDEX
    Explanations

    references to the superhero "Wonder Woman"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "Wonder Woman."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ornia
    -0.80
    aution
    -0.80
    igree
    -0.79
    EStream
    -0.78
    ournal
    -0.78
    alach
    -0.75
     confir
    -0.73
    uckland
    -0.73
    heastern
    -0.73
     srf
    -0.72
    POSITIVE LOGITS
     Woman
    0.92
     Wonder
    0.89
    frey
    0.82
    bolt
    0.82
    stru
    0.78
    power
    0.78
    storms
    0.77
     Beasts
    0.76
     Squid
    0.75
     Meter
    0.75
    Activations Density 0.009%

    No Known Activations