© 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. 24123
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performances and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries and athletic performance

    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
     GOODMAN
    -0.90
    ardon
    -0.72
     Detect
    -0.70
    Detect
    -0.66
    scribe
    -0.65
     Yesterday
    -0.65
    \">
    -0.65
    }}}
    -0.64
     Detection
    -0.64
     Contains
    -0.63
    POSITIVE LOGITS
     plummeted
    1.20
     struggled
    1.18
     bounced
    1.18
     slumped
    1.09
     fal
    1.09
     faded
    1.07
     suffered
    1.05
     derailed
    1.04
     wound
    1.03
     langu
    1.02
    Activations Density 0.325%

    No Known Activations