© 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. 2307
    Prev
    Next
    INDEX
    Explanations

    the symbol "Ċ" appearing multiple times in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or counts related to specific events

    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
    heit
    -0.73
     offline
    -0.63
     everywhere
    -0.58
     Catal
    -0.57
     everyday
    -0.56
     temptation
    -0.55
     sustainability
    -0.55
     moderation
    -0.55
     extrad
    -0.55
     Vald
    -0.55
    POSITIVE LOGITS
    PHOTOS
    1.05
    Scroll
    1.02
    SPONSORED
    0.96
    Specifically
    0.91
    However
    0.81
    ADVERTISEMENT
    0.75
    ramid
    0.75
    Asked
    0.75
    Bus
    0.74
    SEE
    0.73
    Activations Density 0.418%

    No Known Activations