© 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. 3-RES-JB
    11. 3312
    Prev
    Next
    INDEX
    Explanations

    ambiguous or uncertain statements

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating clarity or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eatures
    -0.95
    alez
    -0.85
    unte
    -0.82
    uld
    -0.70
    irl
    -0.69
     crow
    -0.65
    elaide
    -0.64
    olt
    -0.62
    Lie
    -0.62
    Sing
    -0.62
    POSITIVE LOGITS
    ances
    1.05
     clear
    0.92
     sailing
    0.82
    ance
    0.82
     clears
    0.79
    clear
    0.77
     enough
    0.77
    houses
    0.76
    iary
    0.74
    ãĥķãĤ©
    0.71
    Activations Density 0.021%

    No Known Activations