© 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. 6604
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals holding editorial positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "editor" in various contexts

    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
    pered
    -0.79
    bley
    -0.77
    bones
    -0.73
    pering
    -0.73
    achi
    -0.73
    ptoms
    -0.71
    enegger
    -0.68
    ulia
    -0.67
    rises
    -0.66
     Territories
    -0.66
    POSITIVE LOGITS
    ials
    1.11
    ially
    1.07
    editor
    0.85
    furt
    0.78
    ienne
    0.74
    itatively
    0.73
     editor
    0.71
     laureate
    0.69
     Picks
    0.67
    iola
    0.66
    Activations Density 0.016%

    No Known Activations