© 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. 8-RES-JB
    11. 3877
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the usage or applicability of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the potential uses and applications of a subject or tool

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onso
    -0.77
    raint
    -0.72
    urden
    -0.69
    Gov
    -0.68
    Ore
    -0.66
     Dracula
    -0.64
    urance
    -0.64
    rant
    -0.62
    ucha
    -0.62
     ObamaCare
    -0.62
    POSITIVE LOGITS
     optionally
    1.38
     alternatively
    1.19
     manually
    1.04
     abbrevi
    0.97
     optional
    0.94
     either
    0.93
     omitted
    0.90
     vary
    0.90
     varied
    0.89
     vari
    0.87
    Activations Density 0.232%

    No Known Activations