© 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. 15217
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or military entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific television shows or series

    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
    hammad
    -0.81
    etically
    -0.74
    ventus
    -0.73
    font
    -0.73
    esis
    -0.73
    #$
    -0.72
    colour
    -0.71
    cious
    -0.70
    escription
    -0.70
    veyard
    -0.69
    POSITIVE LOGITS
    anches
    0.91
     Feldman
    0.71
    CTV
    0.70
    iable
    0.68
    enegger
    0.68
     aval
    0.67
    ieri
    0.63
     Sunny
    0.62
     converge
    0.61
     REPORT
    0.61
    Activations Density 0.029%

    No Known Activations