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. 8-RES-JB
    6. 238
    Prev
    Next
    INDEX
    Explanations

    words related to physical security and protection, particularly in the context of escorting or safeguarding individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "esc" or variations of it, likely relating to escape or escaping themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuck
    -0.69
    beard
    -0.68
    WARE
    -0.65
     partName
    -0.65
     GUN
    -0.64
     Lakes
    -0.62
    gaard
    -0.62
    ivities
    -0.61
     living
    -0.60
     Kos
    -0.60
    POSITIVE LOGITS
    apist
    1.26
    ribed
    1.23
    adr
    1.03
    aped
    1.02
    orts
    0.99
    ounters
    0.96
    ribing
    0.96
    udos
    0.95
    aline
    0.95
    retion
    0.95
    Activations Density 0.035%

    No Known Activations