© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19034
    Prev
    Next
    INDEX
    Explanations

    sentences that end in a period followed by a high-stakes statement or situation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illet
    -0.84
     satell
    -0.79
    ascus
    -0.77
    ptin
    -0.75
    EStreamFrame
    -0.73
    ãĥ¯ãĥ³
    -0.73
     tradem
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.71
    orescence
    -0.69
     neighb
    -0.68
    POSITIVE LOGITS
     Presumably
    1.17
     Sounds
    1.13
     Furthermore
    1.11
     Similarly
    1.11
     Additionally
    1.09
     Moreover
    1.07
     Meanwhile
    1.06
     Apparently
    1.06
     However
    1.05
     Likewise
    1.05
    Activations Density 0.104%

    No Known Activations