© 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. 9-RES-JB
    11. 1877
    Prev
    Next
    INDEX
    Explanations

    color-related words

    oai_token-act-pair · gpt-3.5-turbo

    mentions of color-coded regions and their significance in a data representation context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     virginity
    -0.71
     Reincarn
    -0.67
    ifi
    -0.64
    ologne
    -0.63
    orous
    -0.63
    kie
    -0.63
    onse
    -0.62
    killing
    -0.62
    apon
    -0.61
    conservancy
    -0.60
    POSITIVE LOGITS
     arrows
    1.17
     dotted
    1.13
     squares
    1.12
     dots
    1.12
     aster
    1.11
     ital
    1.10
     columns
    1.09
     denote
    1.09
     graphs
    1.09
     parentheses
    1.07
    Activations Density 0.319%

    No Known Activations