© 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. 8-RES-JB
    11. 2343
    Prev
    Next
    INDEX
    Explanations

    questions or exclamations in the form of statements followed by punctuation marks like '?', '!', or '.'

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions and expressions of doubt or reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sels
    -0.77
    ancies
    -0.69
    ¥ŀ
    -0.66
    ãĥĭ
    -0.63
    imar
    -0.62
    ¨
    -0.62
    éĹĺ
    -0.61
     habit
    -0.61
    ciplinary
    -0.61
    çĶ°
    -0.61
    POSITIVE LOGITS
     Then
    0.96
    /"
    0.90
     Because
    0.90
     Obviously
    0.89
     Luckily
    0.86
     whereas
    0.85
     Nobody
    0.84
     Knowing
    0.84
    laughter
    0.84
     Sometimes
    0.82
    Activations Density 0.120%

    No Known Activations