© 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. 10134
    Prev
    Next
    INDEX
    Explanations

    terms related to sports, sports events, and athletes

    oai_token-act-pair · gpt-3.5-turbo

    references to entertainment and pop culture

    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
     broadly
    -0.83
     potentially
    -0.81
     fundamentally
    -0.79
     arbitrarily
    -0.79
     unfavorable
    -0.74
     determining
    -0.74
     categor
    -0.73
     relatively
    -0.73
     worrisome
    -0.72
     declining
    -0.72
    POSITIVE LOGITS
     Productions
    0.90
     Remix
    0.90
     Lounge
    0.85
    leigh
    0.80
     Featuring
    0.80
    ventures
    0.78
     Films
    0.77
    aughs
    0.77
     Photography
    0.76
     Orchestra
    0.76
    Activations Density 0.540%

    No Known Activations