© 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. 9613
    Prev
    Next
    INDEX
    Explanations

    descriptions of different scenes

    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
    inness
    -0.65
    brand
    -0.64
    wcsstore
    -0.64
     lifestyles
    -0.63
    protein
    -0.63
    aptop
    -0.61
     consortium
    -0.61
    Own
    -0.61
    recy
    -0.61
    ether
    -0.61
    POSITIVE LOGITS
     verse
    0.91
     passages
    0.88
     verses
    0.87
    Dialogue
    0.86
     excerpts
    0.85
     climax
    0.81
    ologue
    0.80
     finale
    0.80
     segments
    0.79
     opener
    0.78
    Activations Density 0.609%

    No Known Activations