© 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. 21539
    Prev
    Next
    INDEX
    Explanations

    mentions of live events or broadcasts

    oai_token-act-pair · gpt-3.5-turbo

    references to live-action productions

    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
     goodbye
    -0.76
     Zup
    -0.71
     aster
    -0.71
     limp
    -0.70
     Nieto
    -0.69
     magnitude
    -0.69
     susceptibility
    -0.67
     curve
    -0.66
     needing
    -0.65
     favoured
    -0.65
    POSITIVE LOGITS
    action
    1.18
    stream
    1.12
    motion
    1.01
    saving
    0.98
    cation
    0.98
    blog
    0.98
    learning
    0.97
    music
    0.96
    fire
    0.95
    layout
    0.95
    Activations Density 0.026%

    No Known Activations