© 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 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. 6195
    Prev
    Next
    INDEX
    Explanations

    questions or statements directed at oneself

    oai_token-act-pair · gpt-3.5-turbo

    reflections and self-inquiry questions

    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
    oided
    -0.85
    imet
    -0.67
    iba
    -0.60
    atten
    -0.59
     Coverage
    -0.58
    absor
    -0.56
    acements
    -0.54
    ulla
    -0.54
    ouls
    -0.54
    eland
    -0.54
    POSITIVE LOGITS
     why
    1.18
     WHY
    1.09
    why
    0.97
     aloud
    0.97
     questions
    0.93
     whether
    0.89
     how
    0.86
     plaint
    0.85
     "{
    0.85
     rhet
    0.85
    Activations Density 0.100%

    No Known Activations