© 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. 8-RES-JB
    11. 11367
    Prev
    Next
    INDEX
    Explanations

    chemical compound names

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and their characteristics

    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
     careers
    -0.74
    issance
    -0.72
     Generations
    -0.71
    Pause
    -0.69
    entry
    -0.68
     sighting
    -0.68
    ittees
    -0.68
     Views
    -0.67
    FontSize
    -0.67
     Inquiry
    -0.67
    POSITIVE LOGITS
    anol
    1.31
     sodium
    1.31
    amphetamine
    1.31
     salts
    1.30
    methyl
    1.28
     ammonia
    1.27
     potassium
    1.26
    aldehyde
    1.25
     Sodium
    1.25
     ethanol
    1.24
    Activations Density 0.704%

    No Known Activations