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. 23964
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "vis" or "visit."

    oai_token-act-pair · gpt-3.5-turbo

    words related to visual representation or visibility

    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
    Ĥª
    -0.77
    ¶ħ
    -0.76
    RAW
    -0.73
    ropy
    -0.67
    anyahu
    -0.66
     CLR
    -0.60
     Carnegie
    -0.60
     overload
    -0.60
     manners
    -0.59
    riad
    -0.58
    POSITIVE LOGITS
    ibility
    1.27
    ibly
    1.08
    itors
    1.08
    ited
    1.06
    itation
    0.87
    itor
    0.86
    peed
    0.86
    idon
    0.86
     versa
    0.85
    itism
    0.85
    Activations Density 0.013%

    No Known Activations