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. 0-RES-JB
    6. 10855
    Prev
    Next
    INDEX
    Explanations

    phrases related to camps or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "camp."

    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
    MIT
    -0.81
    phies
    -0.71
    Product
    -0.71
    Published
    -0.69
     RELEASE
    -0.68
    poral
    -0.67
     Registrar
    -0.65
    umerable
    -0.64
    ãĥĥãĤ¯
    -0.64
    Downloadha
    -0.64
    POSITIVE LOGITS
     camp
    4.10
     camps
    3.08
    camp
    2.51
     Camp
    2.37
    Camp
    2.08
     encamp
    1.88
     camping
    1.73
     tents
    1.62
     tent
    1.48
     caravan
    1.07
    Activations Density 0.010%

    No Known Activations