© 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. 9912
    Prev
    Next
    INDEX
    Explanations

    mentions of someone going all out or to the extreme in their actions or behavior

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intensity or absoluteness

    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
    ourses
    -0.90
    án
    -0.83
    SPONSORED
    -0.80
     furthermore
    -0.79
    iffs
    -0.79
    enes
    -0.77
    ells
    -0.76
    roups
    -0.76
    perhaps
    -0.76
    atches
    -0.76
    POSITIVE LOGITS
     underdog
    0.88
     spoiler
    0.76
     Ninja
    0.75
     badass
    0.75
     pirate
    0.75
     renaissance
    0.75
     boring
    0.74
     plagiar
    0.73
     crappy
    0.73
     cheesy
    0.73
    Activations Density 0.370%

    No Known Activations