© 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. 1993
    Prev
    Next
    INDEX
    Explanations

    references to checking out related resources or content

    oai_token-act-pair · gpt-3.5-turbo

    references to previous content or resources provided by the author

    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
    omorph
    -0.76
    Reviewer
    -0.69
    UTC
    -0.69
    oldemort
    -0.69
    needed
    -0.69
    okemon
    -0.68
    cells
    -0.68
    endants
    -0.66
    urs
    -0.66
    turned
    -0.65
    POSITIVE LOGITS
     own
    0.96
     interactive
    0.93
     handy
    0.92
     extensive
    0.91
     upcoming
    0.90
     infographic
    0.89
     exhaustive
    0.89
     latest
    0.89
     preview
    0.88
     blog
    0.88
    Activations Density 0.168%

    No Known Activations