© 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. 17317
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "haven"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "aven," which may refer to a specific place or context in the document

    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
     mathemat
    -0.72
     gobl
    -0.67
    ogram
    -0.65
     FINAL
    -0.63
    oric
    -0.63
    izoph
    -0.63
     charism
    -0.62
     cryst
    -0.61
     tyr
    -0.60
    enegger
    -0.60
    POSITIVE LOGITS
    ski
    0.97
    gin
    0.88
    ger
    0.88
    fold
    0.83
    vier
    0.80
    ations
    0.79
    sky
    0.78
    atory
    0.78
    vid
    0.78
    ated
    0.77
    Activations Density 0.048%

    No Known Activations