© 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. 10322
    Prev
    Next
    INDEX
    Explanations

    content that outlines or provides detailed information about various topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "outline" and its variations in a context related to describing plans or frameworks

    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
     nose
    -0.68
     [+
    -0.63
     artifact
    -0.62
    iston
    -0.61
     noses
    -0.61
    thing
    -0.60
    cgi
    -0.60
    Anderson
    -0.60
    taboola
    -0.59
    Ton
    -0.58
    POSITIVE LOGITS
     outlines
    1.28
     outline
    1.12
     outlining
    1.01
     detailing
    0.75
    WER
    0.73
     guidelines
    0.72
     outlined
    0.69
    krit
    0.68
    umenthal
    0.68
    ocument
    0.68
    Activations Density 0.039%

    No Known Activations