© 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. 11-RES-JB
    11. 7153
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal involvement and pleas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plugs
    -0.65
     payday
    -0.64
    ulative
    -0.62
    clips
    -0.62
     Everyday
    -0.58
     Tooth
    -0.57
    rities
    -0.57
     salaries
    -0.56
     clicks
    -0.56
     Hebdo
    -0.56
    POSITIVE LOGITS
     guilty
    1.18
     Guilty
    0.97
     bond
    0.89
     criminally
    0.86
     compe
    0.83
     competent
    0.81
    cause
    0.77
     convicted
    0.77
    yond
    0.72
    prison
    0.72
    Activations Density 0.119%

    No Known Activations