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. 6-RES-JB
    6. 24266
    Prev
    Next
    INDEX
    Explanations

    references to presentations or reports, specifically involving a person or entity named "Pres" or "Presumably"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Pres" or its variants, indicating discussions related to presidents or presidential topics

    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
     brackets
    -0.71
     Lions
    -0.71
     dots
    -0.69
    ISM
    -0.64
     Abyssal
    -0.64
     Salvation
    -0.64
     IMAGES
    -0.64
     Welsh
    -0.64
     Italians
    -0.63
     Worlds
    -0.62
    POSITIVE LOGITS
    cription
    1.24
    chool
    1.23
    ervation
    1.16
    umed
    1.12
    idency
    1.09
    erves
    1.09
    byter
    1.07
    cribed
    1.07
    ervative
    1.06
    erving
    1.05
    Activations Density 0.022%

    No Known Activations