© 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. 21788
    Prev
    Next
    INDEX
    Explanations

    the phrase "in fact" in texts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in fact" and its variations within the text

    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
     Flavoring
    -0.69
    bye
    -0.66
     Citiz
    -0.62
     laure
    -0.62
     Crown
    -0.62
    illed
    -0.60
    ittal
    -0.60
    MENTS
    -0.60
    anon
    -0.59
    ution
    -0.58
    POSITIVE LOGITS
    ional
    0.93
    netflix
    0.86
    ãĥĩãĤ£
    0.73
    olkien
    0.72
    REP
    0.71
    akes
    0.70
    lie
    0.67
     managed
    0.65
     staged
    0.65
    opus
    0.65
    Activations Density 0.023%

    No Known Activations