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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 3192
    Prev
    Next
    INDEX
    Explanations

    references to the human buttocks

    oai_token-act-pair · gpt-3.5-turbo

    references to "butt" in various contexts

    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
    xual
    -0.84
    vous
    -0.83
    vernment
    -0.69
    HCR
    -0.68
    CHO
    -0.68
    SPONSORED
    -0.64
     Suc
    -0.63
    vt
    -0.63
     antidepressants
    -0.62
    ItemImage
    -0.61
    POSITIVE LOGITS
     butt
    1.08
    butt
    1.05
     cheeks
    1.03
    plug
    0.87
     Butt
    0.85
    resses
    0.84
    hest
    0.83
    ress
    0.80
    ocks
    0.79
    ressing
    0.79
    Activations Density 0.009%

    No Known Activations