© 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. 10-RES-JB
    11. 12791
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and requirements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "by" indicating agency or actions performed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bard
    -0.82
    heimer
    -0.79
    bian
    -0.76
    thal
    -0.73
    hene
    -0.70
    bach
    -0.70
    ilight
    -0.70
    allo
    -0.69
    ivas
    -0.69
    eta
    -0.68
    POSITIVE LOGITS
     virtue
    1.37
    products
    1.12
     means
    1.07
    laws
    1.00
     implication
    0.97
     default
    0.96
     fiat
    0.96
     proxy
    0.92
     omission
    0.92
     outsiders
    0.90
    Activations Density 0.145%

    No Known Activations