© 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. 10-RES-JB
    11. 10274
    Prev
    Next
    INDEX
    Explanations

    questions related to experiences and emotions

    oai_token-act-pair · gpt-3.5-turbo

    questions directed at individuals about their feelings, experiences, or opinions

    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
    seless
    -0.78
    acity
    -0.73
    $$$$
    -0.73
    ospace
    -0.67
     Worse
    -0.67
    cession
    -0.66
     Stupid
    -0.66
    .")
    -0.66
     Godd
    -0.65
    udicrous
    -0.62
    POSITIVE LOGITS
     yourselves
    0.99
     yourself
    0.99
    ?ãĢį
    0.93
    )?
    0.87
     your
    0.76
     experien
    0.76
     autobi
    0.73
    ?:
    0.73
    .?
    0.72
    ?
    0.71
    Activations Density 0.261%

    No Known Activations