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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 22417
    Prev
    Next
    INDEX
    Explanations

    references to the color black

    oai_token-act-pair · gpt-3.5-turbo

    the term "black" in various contexts related to people, culture, and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTERS
    -0.93
    OPLE
    -0.90
    =-=-=-=-
    -0.88
    DCS
    -0.86
    _-
    -0.85
    ablishment
    -0.79
    xon
    -0.77
    ICLE
    -0.76
    rative
    -0.76
    PsyNetMessage
    -0.76
    POSITIVE LOGITS
     blacks
    1.04
    berry
    1.03
    smith
    1.02
    black
    1.01
     black
    1.01
     violet
    0.99
    jack
    0.94
     widow
    0.94
    moon
    0.91
     colored
    0.86
    Activations Density 0.024%

    No Known Activations