© 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. 10-RES-JB
    11. 9925
    Prev
    Next
    INDEX
    Explanations

    mentions of different forms of abuse

    oai_token-act-pair · gpt-3.5-turbo

    references to instances of abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izen
    -0.79
    travel
    -0.77
    cil
    -0.72
    pard
    -0.72
    views
    -0.68
    soType
    -0.68
    ebus
    -0.67
     compr
    -0.65
     Towns
    -0.64
    zig
    -0.62
    POSITIVE LOGITS
    abuse
    1.05
     perpetrated
    1.04
     inflicted
    0.99
     abuse
    0.97
     victims
    0.93
     abusing
    0.93
     survivors
    0.90
     abusers
    0.89
     allegations
    0.86
     abuses
    0.85
    Activations Density 0.042%

    No Known Activations