© 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. 8-RES-JB
    11. 9474
    Prev
    Next
    INDEX
    Explanations

    official statements from individuals

    oai_token-act-pair · gpt-3.5-turbo

    reports or statements from various sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Honest
    -0.89
    etsy
    -0.84
    otin
    -0.84
    CLA
    -0.76
    idge
    -0.75
    gray
    -0.75
    bench
    -0.75
    pter
    -0.73
    hook
    -0.73
    bill
    -0.72
    POSITIVE LOGITS
    istani
    0.91
     Daesh
    0.89
     Boko
    0.86
     Houth
    0.86
     explosions
    0.84
     YPG
    0.84
     separatists
    0.82
     Hezbollah
    0.81
     separatist
    0.81
     gunmen
    0.80
    Activations Density 0.264%

    No Known Activations