© 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. 12-RES-JB
    11. 2989
    Prev
    Next
    INDEX
    Explanations

    profane and derogatory language, particularly insults

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    derogatory language and insults directed towards individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourses
    -0.73
     residences
    -0.70
    Enlarge
    -0.67
    seekers
    -0.67
     Flavoring
    -0.67
    isSpecialOrderable
    -0.66
    ILA
    -0.64
     Seasons
    -0.64
    tracks
    -0.63
     arrangements
    -0.63
    POSITIVE LOGITS
     cunt
    1.52
     asshole
    1.49
     idiot
    1.43
     retard
    1.43
     bitch
    1.42
     whore
    1.32
     bastard
    1.29
     slut
    1.27
     jerk
    1.27
     loser
    1.25
    Activations Density 0.342%

    No Known Activations