© 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. 7-RES-JB
    11. 9644
    Prev
    Next
    INDEX
    Explanations

    keywords or questions related to questions or topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     migration
    -0.86
     inactive
    -0.73
     transition
    -0.72
     hust
    -0.69
     phased
    -0.69
     migr
    -0.69
     sprint
    -0.68
     exiting
    -0.68
     sacked
    -0.68
     salv
    -0.66
    POSITIVE LOGITS
    Answer
    1.63
    Well
    1.14
     Answer
    1.08
    Perhaps
    1.02
    Solution
    1.01
    Probably
    1.00
    Certainly
    1.00
    ccording
    1.00
    Consider
    0.99
    YES
    0.99
    Activations Density 0.159%

    No Known Activations