© 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. 2266
    Prev
    Next
    INDEX
    Explanations

    terms related to technological operations and processes

    oai_token-act-pair · gpt-3.5-turbo
    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
    lihood
    -0.81
    depth
    -0.63
     grading
    -0.63
    anship
    -0.61
    vier
    -0.59
    earch
    -0.58
     brightest
    -0.58
    Redd
    -0.58
    nai
    -0.57
    iar
    -0.57
    POSITIVE LOGITS
     somebody
    0.71
    ouched
    0.67
     theirs
    0.66
    ratulations
    0.63
     THESE
    0.62
    âĶĢâĶĢ
    0.61
     yours
    0.61
    70710
    0.61
     these
    0.59
     ONE
    0.59
    Activations Density 0.869%

    No Known Activations