© 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. 3-RES-JB
    11. 20486
    Prev
    Next
    INDEX
    Explanations

    words related to difficulties or problems

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "trouble"

    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
    oliberal
    -0.79
    ulture
    -0.77
    obook
    -0.72
    ams
    -0.71
    ry
    -0.69
    oven
    -0.69
    orney
    -0.68
    ithe
    -0.68
    hetically
    -0.67
    æĺ¯
    -0.67
    POSITIVE LOGITS
    hooting
    0.97
     trouble
    0.90
     troubles
    0.87
    makers
    0.76
    INESS
    0.74
    flake
    0.73
    chief
    0.73
    fully
    0.72
     headaches
    0.71
     plag
    0.71
    Activations Density 0.023%

    No Known Activations