© 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. 7728
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts to contact someone for a comment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to communication attempts or contact

    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
    Ranked
    -0.62
    coming
    -0.57
     subp
    -0.56
     pudding
    -0.55
    ilib
    -0.54
    ierre
    -0.54
    ±
    -0.54
    Being
    -0.53
    hire
    -0.53
    rival
    -0.53
    POSITIVE LOGITS
     anonymously
    0.81
    ALSE
    0.77
     by
    0.76
    zanne
    0.76
     via
    0.72
     separately
    0.70
    yll
    0.69
     pione
    0.69
     unsuccessfully
    0.68
    leigh
    0.67
    Activations Density 0.080%

    No Known Activations