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. 11-RES-JB
    6. 8793
    Prev
    Next
    INDEX
    Explanations

    negative connotations or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "suck" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.78
    ouf
    -0.75
    thumbnails
    -0.72
    Correct
    -0.71
    merce
    -0.71
    isable
    -0.68
    teness
    -0.67
     è£ıç
    -0.67
    iferation
    -0.66
    DonaldTrump
    -0.65
    POSITIVE LOGITS
     dick
    1.06
    tails
    0.86
     suck
    0.85
     sucking
    0.82
     breaths
    0.82
     cock
    0.82
     moisture
    0.81
     saliva
    0.79
    oway
    0.78
    asses
    0.77
    Activations Density 0.082%

    No Known Activations