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. 6-RES-JB
    6. 22237
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "rude" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "dude" and its variations in different contexts

    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
    ãĥ£
    -0.92
     ILCS
    -0.89
    awaru
    -0.88
    riors
    -0.81
    marked
    -0.79
    pora
    -0.79
    stall
    -0.77
    olulu
    -0.76
    iott
    -0.75
    apesh
    -0.75
    POSITIVE LOGITS
    gger
    0.77
    anu
    0.76
    xual
    0.74
    uces
    0.74
    cker
    0.72
    mber
    0.69
    icone
    0.69
    lder
    0.68
    geries
    0.67
     Olson
    0.67
    Activations Density 0.028%

    No Known Activations