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. 11-RES-JB
    6. 20028
    Prev
    Next
    INDEX
    Explanations

    text related to a specific technology or platform called "Tor"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tor network

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naires
    -0.78
     Dakota
    -0.66
     XV
    -0.62
     Eisenhower
    -0.62
     bargaining
    -0.61
     Feder
    -0.60
     FAT
    -0.59
     Continental
    -0.59
     Presidents
    -0.59
     gener
    -0.58
    POSITIVE LOGITS
    onto
    1.32
    mented
    1.29
    rance
    1.22
    bj
    1.09
    sten
    1.07
    rington
    1.07
    ped
    1.06
    reon
    1.04
    rent
    1.02
    por
    0.98
    Activations Density 0.038%

    No Known Activations