© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16400
    Prev
    Next
    INDEX
    Explanations

    references to inappropriate behavior or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances or discussions of inappropriate behavior or conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rix
    -0.86
    ership
    -0.82
    stone
    -0.78
    track
    -0.78
    stones
    -0.76
    prototype
    -0.76
    ynthesis
    -0.76
    abiding
    -0.75
    fighters
    -0.74
    raq
    -0.74
    POSITIVE LOGITS
     inappropriate
    1.00
     improper
    0.97
     behaviour
    0.88
     interference
    0.88
     indisc
    0.84
     misuse
    0.84
     behavior
    0.81
     misconduct
    0.81
     improperly
    0.79
     allegations
    0.79
    Activations Density 0.016%

    No Known Activations