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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16791
    Prev
    Next
    INDEX
    Explanations

    profane and derogatory language

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "bullshit" and related phrases expressing disdain or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cort
    -0.73
    lav
    -0.68
     mut
    -0.68
     migr
    -0.67
    acan
    -0.63
     Morton
    -0.63
    roid
    -0.62
    rog
    -0.62
     pond
    -0.62
    arter
    -0.62
    POSITIVE LOGITS
     BS
    3.96
     bullshit
    1.87
    BS
    1.58
     BA
    1.35
     ABS
    1.34
     BG
    1.27
    bps
    1.23
     Bers
    1.08
     BM
    1.03
     BF
    1.02
    Activations Density 0.026%

    No Known Activations