© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1020
    Prev
    Next
    INDEX
    Explanations

    unusual characters or sequences within text

    oai_token-act-pair · gpt-3.5-turbo

    ambiguous or generic statements that lack specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.92
    atis
    -0.69
    olicy
    -0.69
     estranged
    -0.68
     inactive
    -0.68
    emort
    -0.66
    ibrary
    -0.66
    arde
    -0.65
    ensibly
    -0.65
    uly
    -0.64
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.14
    ³³³³³³³³
    1.12
    ³³³³
    1.06
    Anyway
    1.05
    ³³³
    0.95
    ³³
    0.94
     Anyway
    0.90
    Anonymous
    0.90
    ONSORED
    0.87
    Posted
    0.86
    Activations Density 0.418%

    No Known Activations