© 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. 6-RES-JB
    11. 1037
    Prev
    Next
    INDEX
    Explanations

    negative content related to violence, discrimination, and offensive language

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and intolerance towards various identity groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onen
    -0.57
     Mous
    -0.56
    noon
    -0.52
     Dangerous
    -0.52
     Nich
    -0.51
     Piper
    -0.51
    lyak
    -0.50
    20439
    -0.50
     Passage
    -0.50
     Architects
    -0.50
    POSITIVE LOGITS
     etc
    1.20
    etc
    1.01
    âĢ¦)
    0.84
    whatever
    0.71
     ect
    0.68
    âĢ¦
    0.65
    cknow
    0.61
    cheat
    0.60
     welf
    0.58
     âĢ¦
    0.58
    Activations Density 0.372%

    No Known Activations