© 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. 7840
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or judicial contexts

    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
     TS
    -0.98
     mathemat
    -0.87
     Hitch
    -0.85
     Somers
    -0.83
     Jericho
    -0.73
     Chak
    -0.71
    rets
    -0.71
     Sussex
    -0.70
     Sar
    -0.70
    ModLoader
    -0.70
    POSITIVE LOGITS
    Ļ
    1.15
    inois
    0.96
    ħ
    0.85
    aign
    0.84
    âĢł
    0.82
    ÃĤ
    0.80
    adin
    0.79
    Ä«
    0.78
    inator
    0.78
    âĢ
    0.77
    Activations Density 0.155%

    No Known Activations