© 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. 9-RES-JB
    11. 17076
    Prev
    Next
    INDEX
    Explanations

    brightly colored and intensively illuminated things

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that describe intensity or manner

    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
    eday
    -0.77
    arella
    -0.75
    raltar
    -0.73
    ĺħ
    -0.73
    ĸļ
    -0.73
    oons
    -0.72
    oleon
    -0.71
    ydia
    -0.71
     Tycoon
    -0.71
    vana
    -0.69
    POSITIVE LOGITS
     occurring
    0.99
    accessible
    0.85
     spaced
    0.85
     distributed
    0.84
     identifiable
    0.84
    existing
    0.83
     coded
    0.83
     vaccinated
    0.82
     populated
    0.82
     constructed
    0.82
    Activations Density 0.204%

    No Known Activations