© 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. 3089
    Prev
    Next
    INDEX
    Explanations

    speculative statements or possibilities indicated by the word "that" followed by a verb or noun

    oai_token-act-pair · gpt-3.5-turbo
    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
    ãĥīãĥ©
    -0.82
    ario
    -0.71
    verend
    -0.70
    ãĤ´
    -0.70
    apsed
    -0.69
    olphin
    -0.66
    83
    -0.66
    arest
    -0.66
    ãĥĸ
    -0.65
    Rated
    -0.65
    POSITIVE LOGITS
     maybe
    0.95
     perhaps
    0.87
    might
    0.86
     hint
    0.84
     possibly
    0.84
     possibility
    0.79
     motives
    0.78
    perhaps
    0.77
    maybe
    0.76
     speculate
    0.75
    Activations Density 0.261%

    No Known Activations