© 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. 22634
    Prev
    Next
    INDEX
    Explanations

    descriptions related to specific events or actions happening in a narrative or a game

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hostage situations and their implications

    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
    yz
    -1.01
    esame
    -0.85
     cereal
    -0.85
     balloon
    -0.84
     Kramer
    -0.84
    zona
    -0.81
    vana
    -0.80
     balloons
    -0.80
    tube
    -0.78
    ucha
    -0.78
    POSITIVE LOGITS
     Assassin
    1.91
     Assassins
    1.73
     Ubisoft
    1.72
     Creed
    1.46
     Spectre
    1.46
     Thief
    1.45
     Templ
    1.43
    isoft
    1.36
     Templar
    1.35
     Hitman
    1.34
    Activations Density 0.143%

    No Known Activations