© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17084
    Prev
    Next
    INDEX
    Explanations

    critical instructions or steps in a process

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to strategy and performance in sports

    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
     Membership
    -0.93
     unaff
    -0.82
     Homeless
    -0.80
     subsidized
    -0.77
    ylum
    -0.75
     tarn
    -0.75
    married
    -0.74
     landfill
    -0.73
     donated
    -0.72
    Ń·
    -0.71
    POSITIVE LOGITS
     manoeuv
    1.29
     positioning
    1.28
     maneuvers
    1.18
     instinctively
    1.18
     reflex
    1.18
     positional
    1.18
     tempo
    1.17
     cues
    1.15
     timing
    1.15
     technique
    1.14
    Activations Density 0.652%

    No Known Activations