© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6472
    Prev
    Next
    INDEX
    Explanations

    text related to explanations or processes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal preferences or aversions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aspers
    -0.83
     whistlebl
    -0.78
     exits
    -0.74
    netflix
    -0.73
     CNS
    -0.72
     mosqu
    -0.71
     Exit
    -0.71
     Immunity
    -0.69
     systemd
    -0.69
     Outbreak
    -0.68
    POSITIVE LOGITS
     sculpt
    1.82
     sket
    1.50
     drawings
    1.43
     sketches
    1.43
     painting
    1.34
     sculpture
    1.32
     Designs
    1.29
     sketch
    1.29
     painted
    1.25
     acrylic
    1.25
    Activations Density 0.889%

    No Known Activations