© 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. 3-RES-JB
    11. 15251
    Prev
    Next
    INDEX
    Explanations

    words related to the color black

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "black"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.92
    =-=-=-=-
    -0.92
    ablishment
    -0.85
    OPLE
    -0.84
    ICLE
    -0.78
    igslist
    -0.77
    xon
    -0.76
    ICES
    -0.75
     Lauder
    -0.75
    =-=-
    -0.74
    POSITIVE LOGITS
    smith
    1.20
    berry
    1.05
    jack
    1.02
    moon
    0.95
    ened
    0.95
    hawk
    0.91
    beard
    0.86
     widow
    0.86
     colored
    0.86
    horse
    0.83
    Activations Density 0.034%

    No Known Activations