© 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. 11-RES-JB
    11. 23143
    Prev
    Next
    INDEX
    Explanations

    references to the activity of gliding or slides

    oai_token-act-pair · gpt-3.5-turbo

    references to gliding activities and community engagement

    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
    Cruz
    -0.95
     Chiefs
    -0.86
     Taxi
    -0.77
    uti
    -0.77
    raid
    -0.77
    Uber
    -0.76
    ku
    -0.76
     RC
    -0.75
    tera
    -0.75
    acan
    -0.75
    POSITIVE LOGITS
     Gl
    2.58
    Gl
    2.30
    gl
    2.11
     gl
    2.07
     GL
    2.00
    GL
    1.80
     GF
    1.41
     Glow
    1.33
     Gleaming
    1.33
     Glover
    1.30
    Activations Density 0.196%

    No Known Activations