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. 1-RES-JB
    6. 3043
    Prev
    Next
    INDEX
    Explanations

    terms related to giving permission or approval, such as "clearance."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "clearance"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amed
    -0.71
    eva
    -0.69
    sn
    -0.66
    repl
    -0.66
    ram
    -0.66
    Sn
    -0.66
    rame
    -0.65
    LI
    -0.65
    hed
    -0.65
    sg
    -0.63
    POSITIVE LOGITS
     clearance
    1.69
     waivers
    0.93
     clears
    0.84
     cleared
    0.83
    ACP
    0.77
     certs
    0.76
     paperwork
    0.76
    Ĥª
    0.75
     approvals
    0.73
     clearing
    0.73
    Activations Density 0.008%

    No Known Activations