© 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. 10203
    Prev
    Next
    INDEX
    Explanations

    mentions of the color white

    oai_token-act-pair · gpt-3.5-turbo

    references to "White" in various contexts

    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
    ITAL
    -0.84
    Occup
    -0.76
     WATCHED
    -0.75
    ENDED
    -0.72
    odcast
    -0.71
    cffffcc
    -0.70
    Completed
    -0.70
    obbies
    -0.70
    raints
    -0.70
    INGTON
    -0.67
    POSITIVE LOGITS
    caps
    1.13
    house
    1.09
    berry
    1.03
    horse
    0.99
     supremacist
    0.98
     supremacists
    0.91
    white
    0.89
     White
    0.89
    houses
    0.88
    mouth
    0.86
    Activations Density 0.019%

    No Known Activations