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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8321
    Prev
    Next
    INDEX
    Explanations

    profanity or negative criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stupid" and its variations

    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
     Additional
    -0.80
    orial
    -0.75
    iday
    -0.74
    ures
    -0.68
    esan
    -0.68
    umn
    -0.68
    fulness
    -0.66
    kamp
    -0.64
    Additional
    -0.62
    hurst
    -0.62
    POSITIVE LOGITS
     stupid
    3.13
     Stupid
    2.34
     dumb
    2.12
     stupidity
    2.02
    upid
    1.77
     silly
    1.72
     idiots
    1.71
     shitty
    1.68
     goddamn
    1.62
     retarded
    1.61
    Activations Density 0.015%

    No Known Activations