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. 10-RES-JB
    6. 22704
    Prev
    Next
    INDEX
    Explanations

    mentions of specific symbols, likely part of formatting or special characters

    oai_token-act-pair · gpt-3.5-turbo

    the letter "L" or its variations, indicating a focus on characters or symbols resembling it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DISTR
    -0.65
     Mirage
    -0.62
     pulp
    -0.62
     Moroccan
    -0.59
     Hamm
    -0.59
     Mash
    -0.58
     shack
    -0.58
     Monroe
    -0.58
     Swanson
    -0.58
     Pratt
    -0.57
    POSITIVE LOGITS
    Pg
    0.90
    s
    0.87
    inventoryQuantity
    0.86
    ttp
    0.85
    ept
    0.84
    efined
    0.83
    px
    0.81
    ution
    0.80
    else
    0.80
    owners
    0.76
    Activations Density 0.077%

    No Known Activations