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

    Neuronpedia

    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. 22336
    Prev
    Next
    INDEX
    Explanations

    software-related code snippets

    oai_token-act-pair · gpt-3.5-turbo

    import statements and references to control functionality in programming contexts

    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
    leans
    -0.75
    Hunt
    -0.73
    OPA
    -0.68
    ocene
    -0.68
    lde
    -0.68
    ugal
    -0.65
    MI
    -0.65
     retake
    -0.64
     fry
    -0.63
    headed
    -0.63
    POSITIVE LOGITS
     Vector
    0.93
     std
    0.84
    alias
    0.80
    std
    0.80
     java
    0.74
     Terr
    0.71
     {}
    0.71
     Valiant
    0.71
     Prototype
    0.70
     Foo
    0.69
    Activations Density 0.073%

    No Known Activations