Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14235
    Prev
    Next
    INDEX
    Explanations

    the surname "Lim."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals with the surname "Lim."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dot
    -0.75
    WS
    -0.74
    ${
    -0.68
     WS
    -0.68
    RG
    -0.68
    enta
    -0.66
    isters
    -0.66
    SB
    -0.65
    azon
    -0.65
    atz
    -0.64
    POSITIVE LOGITS
     Lim
    3.80
    Lim
    3.09
     LIM
    1.98
     lim
    1.84
    lim
    1.53
     Limits
    1.51
     Limit
    1.34
     limitations
    1.27
     Lau
    1.23
     limitation
    1.21
    Activations Density 0.017%

    No Known Activations