© 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. 10-RES-JB
    11. 18993
    Prev
    Next
    INDEX
    Explanations

    profane language

    oai_token-act-pair · gpt-3.5-turbo

    references to profanity or vulgar language

    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
    fman
    -0.72
    HCR
    -0.67
    PsyNetMessage
    -0.66
     Parables
    -0.65
    arb
    -0.63
    cffff
    -0.61
    EVA
    -0.61
     Expend
    -0.60
    tnc
    -0.59
     obser
    -0.59
    POSITIVE LOGITS
    loads
    1.22
    bags
    1.19
    storm
    1.16
    heads
    1.10
    lords
    1.06
    faced
    1.06
    bag
    1.03
    post
    1.03
    lord
    0.99
     detector
    0.98
    Activations Density 0.045%

    No Known Activations