© 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. 3875
    Prev
    Next
    INDEX
    Explanations

    hidden captions or identifiers within text or images

    oai_token-act-pair · gpt-3.5-turbo

    references to visual elements or directives in media content

    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
    xf
    -0.88
     Yus
    -0.84
     Must
    -0.82
     shar
    -0.79
     Yo
    -0.77
     Ric
    -0.77
     toug
    -0.76
     Jun
    -0.75
     whis
    -0.74
     sty
    -0.74
    POSITIVE LOGITS
    ulation
    0.91
    itution
    0.90
    TION
    0.87
    position
    0.87
    lation
    0.85
    mission
    0.85
    tion
    0.84
    ument
    0.84
    ression
    0.83
    TERN
    0.83
    Activations Density 0.299%

    No Known Activations