© 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. 9-RES-JB
    11. 14866
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries and setbacks in sports

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports injuries and their impact on performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.98
    },{"
    -0.77
    "}],"
    -0.76
    eva
    -0.76
    orah
    -0.76
    Detect
    -0.74
    \">
    -0.73
    ibo
    -0.72
    zees
    -0.72
    toc
    -0.72
    POSITIVE LOGITS
     plagued
    1.34
     disastrous
    1.32
     setbacks
    1.30
     inexper
    1.28
     botched
    1.24
     sidelined
    1.21
     lackluster
    1.20
     setback
    1.19
     derailed
    1.17
     debacle
    1.17
    Activations Density 0.893%

    No Known Activations