© 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. 18344
    Prev
    Next
    INDEX
    Explanations

    profane language

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong swearing or vulgar language

    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
    eus
    -0.82
    ACP
    -0.78
    idon
    -0.77
    Var
    -0.75
    rist
    -0.74
    Folder
    -0.74
    tis
    -0.73
    ira
    -0.72
    encers
    -0.72
    inel
    -0.72
    POSITIVE LOGITS
     fucking
    1.00
     kidding
    0.95
     fuck
    0.89
     shit
    0.82
     fuckin
    0.82
     prick
    0.79
     useless
    0.77
     goddamn
    0.77
     FUCK
    0.76
     Fuck
    0.75
    Activations Density 0.020%

    No Known Activations