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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3765
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal classifications and levels of severity

    oai_token-act-pair · gpt-3.5-turbo
    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
    ameless
    -0.71
    mosp
    -0.67
    estamp
    -0.66
    uploads
    -0.65
    hammer
    -0.65
    atz
    -0.65
    pload
    -0.64
    eston
    -0.64
    arus
    -0.63
    echo
    -0.63
    POSITIVE LOGITS
    +,
    0.84
     guiActiveUnfocused
    0.81
    +.
    0.80
     designation
    0.74
     Diabetes
    0.74
     diabetes
    0.73
     inhibitor
    0.68
    ZE
    0.65
     classification
    0.65
     Networks
    0.65
    Activations Density 0.104%

    No Known Activations