© 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. 2-RES-JB
    11. 9093
    Prev
    Next
    INDEX
    Explanations

    questioning expressions or prompts

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shaw
    -0.76
    icro
    -0.72
    aper
    -0.71
    ania
    -0.69
    achy
    -0.68
    undo
    -0.68
    arers
    -0.67
    arer
    -0.67
    opsis
    -0.65
    eper
    -0.65
    POSITIVE LOGITS
    .?
    0.98
     ???
    0.89
    ����
    0.88
    ?,
    0.86
     Huh
    0.81
     Nope
    0.77
    soever
    0.77
     Interest
    0.74
    ?:
    0.73
     Nationwide
    0.69
    Activations Density 0.032%

    No Known Activations