© 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. 4-RES-JB
    11. 9415
    Prev
    Next
    INDEX
    Explanations

    words related to profanity and explicit content

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases that are suggestive of explicit content

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

    No Comments

    Negative Logits
    éĹĺ
    -0.78
    £ı
    -0.69
     "$:/
    -0.65
     Congo
    -0.61
    Draft
    -0.60
    ETHOD
    -0.58
    JM
    -0.58
     transitional
    -0.58
    URRENT
    -0.57
    uto
    -0.56
    POSITIVE LOGITS
    alog
    0.60
    istry
    0.60
    jobs
    0.59
    etics
    0.57
    ological
    0.57
    isms
    0.57
    eworthy
    0.57
    ificial
    0.56
     Corpus
    0.55
    yah
    0.55
    Activations Density 0.340%

    No Known Activations