© 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. 23839
    Prev
    Next
    INDEX
    Explanations

    mentions of statements or quotes

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers or statistical information

    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
    xual
    -0.81
     nightly
    -0.72
     casc
    -0.70
     deserts
    -0.67
     commissions
    -0.66
     diminishing
    -0.66
     fors
    -0.66
     perspect
    -0.65
     ourselves
    -0.65
     incent
    -0.65
    POSITIVE LOGITS
    SPONSORED
    1.27
    FILE
    1.23
    Sources
    1.22
    ADVERTISEMENT
    1.20
    Asked
    1.18
    Earlier
    1.18
    Published
    1.18
    Topics
    1.17
    Officials
    1.16
    Copyright
    1.16
    Activations Density 0.401%

    No Known Activations