© 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. 2-RES-JB
    11. 17756
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical violence or assault

    oai_token-act-pair · gpt-3.5-turbo

    references to instances of physical violence or abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     facult
    -0.87
    export
    -0.81
    orrow
    -0.79
    odor
    -0.77
    entric
    -0.76
    gravity
    -0.74
    osion
    -0.74
    aird
    -0.73
    orescent
    -0.70
    ateral
    -0.70
    POSITIVE LOGITS
     beaten
    1.32
    beat
    1.20
    Beat
    1.02
     beating
    0.99
     beat
    0.91
    ¶æ
    0.88
     Beat
    0.88
    heet
    0.86
    boxing
    0.81
     against
    0.74
    Activations Density 0.011%

    No Known Activations