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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5556
    Prev
    Next
    INDEX
    Explanations

    words related to a specific individual or brand named "Dub."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Dub" in various contexts

    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
     [+]
    -0.68
    owship
    -0.64
    yss
    -0.62
    untarily
    -0.61
     liability
    -0.61
    ioned
    -0.61
    =~
    -0.61
    imei
    -0.60
    vector
    -0.60
    enter
    -0.59
    POSITIVE LOGITS
     Dub
    3.92
    Dub
    2.86
     dub
    1.92
     Dum
    1.24
     Dob
    1.18
     Dup
    1.17
     Drum
    1.15
     Pok
    1.09
     Dul
    0.99
     Zub
    0.99
    Activations Density 0.014%

    No Known Activations