© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23674
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a shift in focus or topic, typically introducing a new point or perspective

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "For" indicating a point of emphasis or introduction in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.71
    zona
    -0.69
    marine
    -0.67
    Bu
    -0.59
    arest
    -0.57
     RIGHT
    -0.55
    LAB
    -0.55
    Jr
    -0.54
    Norm
    -0.54
     crawl
    -0.54
    POSITIVE LOGITS
    cing
    1.39
     example
    1.36
    gotten
    1.36
    bidden
    1.35
     instance
    1.32
    ced
    1.14
    give
    1.09
     starters
    1.04
    getting
    1.03
    cible
    1.02
    Activations Density 0.062%

    No Known Activations