© 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. 12347
    Prev
    Next
    INDEX
    Explanations

    mentions of skin color or race

    oai_token-act-pair · gpt-3.5-turbo

    references to race and people of color

    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
    _-
    -0.83
    doms
    -0.82
    idem
    -0.79
    EMS
    -0.74
    minster
    -0.74
    uckland
    -0.72
    iddles
    -0.68
    ODUCT
    -0.67
    ambers
    -0.66
    yu
    -0.66
    POSITIVE LOGITS
    blind
    1.03
     color
    1.00
     palette
    0.97
    color
    0.96
     colors
    0.95
    coat
    0.84
    anguage
    0.83
     tint
    0.82
    ="#
    0.82
     colours
    0.81
    Activations Density 0.016%

    No Known Activations