© 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. 11-RES-JB
    11. 20615
    Prev
    Next
    INDEX
    Explanations

    the word "Anyone" in sentences asking for information or assistance from the community

    oai_token-act-pair · gpt-3.5-turbo

    phrases prompting individuals to provide information or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erenn
    -0.82
    rawdownloadcloneembedreportprint
    -0.78
     Democr
    -0.74
    gemony
    -0.73
    illac
    -0.71
     Flavoring
    -0.71
    iosyncr
    -0.69
    ageddon
    -0.66
    esome
    -0.66
    ospels
    -0.65
    POSITIVE LOGITS
     wishing
    1.09
     contacting
    1.03
     interested
    1.02
     experiencing
    0.96
     concerned
    0.92
     affected
    0.92
     identifying
    0.92
     impacted
    0.90
     involved
    0.90
     accessing
    0.89
    Activations Density 0.070%

    No Known Activations