© 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. 4-RES-JB
    11. 458
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, especially those related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the last name "Chapman."

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

    No Comments

    Negative Logits
    ocene
    -0.80
    uth
    -0.79
    urers
    -0.76
    abeth
    -0.74
    urus
    -0.70
    agers
    -0.70
    erie
    -0.70
    ature
    -0.69
    ager
    -0.68
    acular
    -0.67
    POSITIVE LOGITS
     Chapman
    0.77
    verning
    0.73
    âĸ¬
    0.73
    enance
    0.72
    66666666
    0.72
    lations
    0.71
     GOODMAN
    0.71
    dylib
    0.70
    lication
    0.69
     decomp
    0.69
    Activations Density 0.042%

    No Known Activations