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. 5348
    Prev
    Next
    INDEX
    Explanations

    instances where a performance or role is being repeated or continued by an individual

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "reprising" and various forms of it

    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
    zin
    -0.69
    we
    -0.66
     Cultural
    -0.64
     Publishers
    -0.64
    emn
    -0.64
    Methods
    -0.64
     collectors
    -0.64
    izoph
    -0.64
     ob
    -0.63
     Ob
    -0.63
    POSITIVE LOGITS
    leck
    0.84
    isSpecialOrderable
    0.78
     sidelined
    0.76
    lain
    0.73
     awa
    0.69
    pard
    0.69
    lio
    0.68
     captcha
    0.67
    channelAvailability
    0.66
    iago
    0.66
    Activations Density 0.422%

    No Known Activations