© 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. 7929
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or procedural language

    oai_token-act-pair · gpt-3.5-turbo

    the presence of various symbols or characters that aren't typically found in standard text

    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
     indo
    -0.75
    creen
    -0.72
     board
    -0.69
     Marketable
    -0.69
     detached
    -0.69
     couch
    -0.69
     semblance
    -0.69
     constitution
    -0.68
     shroud
    -0.68
     bung
    -0.68
    POSITIVE LOGITS
    ª
    1.25
    ł
    1.20
    ij
    1.07
    Ĵ
    1.03
    ¹
    1.02
    IJ
    0.99
    ¤
    0.98
    £
    0.95
    ¡
    0.95
    ı
    0.94
    Activations Density 0.099%

    No Known Activations