© 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. 3841
    Prev
    Next
    INDEX
    Explanations

    proper nouns and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    key events or significant moments in narratives

    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
    ggles
    -0.62
    REDACTED
    -0.43
    dozen
    -0.43
    hhh
    -0.43
    seless
    -0.42
    inis
    -0.41
     redacted
    -0.41
    adelphia
    -0.40
    FOX
    -0.39
    dit
    -0.39
    POSITIVE LOGITS
     emphas
    0.52
     organised
    0.51
     Gö
    0.48
     util
    0.46
    ÄŁ
    0.46
     colour
    0.45
     enqu
    0.44
    jriwal
    0.44
     Kazakh
    0.44
     âĵĺ
    0.43
    Activations Density 2.861%

    No Known Activations