© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4183
    Prev
    Next
    INDEX
    Explanations

    statements or comments made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to comments, statements, or claims made by various individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contrace
    -0.65
    izont
    -0.61
     unpop
    -0.61
    inately
    -0.60
    cffffcc
    -0.59
     mating
    -0.59
    psc
    -0.59
    enegger
    -0.59
    enough
    -0.58
    isexual
    -0.58
    POSITIVE LOGITS
     undertaken
    1.08
     uttered
    0.85
     emanating
    0.85
     taken
    0.84
     exchanged
    0.84
     performed
    0.83
     made
    0.79
     done
    0.78
     issued
    0.76
     initiated
    0.75
    Activations Density 0.582%

    No Known Activations