© 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. 7-RES-JB
    11. 20709
    Prev
    Next
    INDEX
    Explanations

    words related to environmental issues and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to location or relation to regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misunder
    -0.73
     delegation
    -0.69
     welf
    -0.69
     mathemat
    -0.65
     Negro
    -0.65
     contrace
    -0.65
     civilian
    -0.64
     stump
    -0.63
     jog
    -0.63
     buggy
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.52
    ï¸
    1.03
    ski
    0.89
    £
    0.82
    sure
    0.82
    worthiness
    0.82
    eric
    0.82
    âĶĢâĶĢ
    0.81
    âĻ
    0.79
    forcing
    0.78
    Activations Density 0.264%

    No Known Activations