© 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. 9613
    Prev
    Next
    INDEX
    Explanations

    words related to profanity and derogatory language

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to frustration or strong emotions

    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
     Advisory
    -0.77
    Preview
    -0.75
     Directorate
    -0.73
     advisory
    -0.71
     CLR
    -0.71
     Cosponsors
    -0.70
     Proceedings
    -0.68
     Assistance
    -0.68
     Associated
    -0.68
     Municipal
    -0.67
    POSITIVE LOGITS
    aaaa
    1.08
     fuckin
    1.08
    aaa
    1.01
    agra
    1.00
    illy
    0.99
     ;)
    0.97
    oooo
    0.96
     fucking
    0.94
    fuck
    0.93
    eeee
    0.93
    Activations Density 0.322%

    No Known Activations