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

    Neuronpedia

    Jacobian LensNEW
    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. 19463
    Prev
    Next
    INDEX
    Explanations

    descriptions or instructions related to a creative process involving drawing or illustration

    oai_token-act-pair · gpt-3.5-turbo

    references to player interactions and game mechanics

    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
    yet
    -0.67
    Nevertheless
    -0.62
    Nonetheless
    -0.61
    azeera
    -0.61
     lacked
    -0.60
     improperly
    -0.59
    ibur
    -0.58
    ubb
    -0.58
    than
    -0.58
    Yet
    -0.57
    POSITIVE LOGITS
     randomly
    1.04
     each
    0.84
     random
    0.82
     brainstorm
    0.81
     predetermined
    0.76
     preferably
    0.75
     periodically
    0.74
    random
    0.73
     squares
    0.73
     whichever
    0.72
    Activations Density 1.118%

    No Known Activations