Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3260
    Prev
    Next
    INDEX
    Explanations

    profanity and offensive words

    oai_token-act-pair · gpt-3.5-turbo

    explicit language and strong expletives

    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
    utterstock
    -0.78
     guiActiveUnfocused
    -0.72
     guiActiveUn
    -0.71
     ancest
    -0.70
     surn
    -0.69
    OSP
    -0.69
     docking
    -0.67
     showc
    -0.66
    Vert
    -0.66
     rece
    -0.66
    POSITIVE LOGITS
    nuts
    0.84
    cr
    0.83
    bah
    0.82
    shit
    0.81
    heads
    0.80
    fuck
    0.77
    peat
    0.75
     nuts
    0.75
    dust
    0.75
    holes
    0.75
    Activations Density 0.021%

    No Known Activations