© 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 EvalsExportsinterp-engineNEWAPI 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. 23190
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of legal terms and concepts

    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
     beh
    -0.76
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.76
     retard
    -0.75
     crumble
    -0.75
     synerg
    -0.72
     deduct
    -0.72
     favors
    -0.71
    ichick
    -0.70
     altern
    -0.69
     triv
    -0.69
    POSITIVE LOGITS
    Former
    1.36
    Published
    1.31
    The
    1.25
    Following
    1.25
    Thousands
    1.25
    Hundreds
    1.24
    Scientists
    1.23
    Updated
    1.23
    An
    1.22
    More
    1.21
    Activations Density 0.122%

    No Known Activations