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. 0-RES-JB
    6. 21824
    Prev
    Next
    INDEX
    Explanations

    the word "onymous" or words containing a similar sound

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "anonymous" and related terms

    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
     mastery
    -0.67
     Revision
    -0.64
    RE
    -0.64
     slack
    -0.63
    AIR
    -0.63
     cram
    -0.62
     wr
    -0.62
     toug
    -0.61
    flex
    -0.61
    GRE
    -0.61
    POSITIVE LOGITS
    onymous
    4.32
    onym
    3.69
    onyms
    3.11
    hemer
    1.19
     Lennon
    1.19
    onomous
    1.19
     anonymously
    1.14
    alog
    1.13
    ampton
    1.08
    agogue
    1.08
    Activations Density 0.035%

    No Known Activations