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. 7225
    Prev
    Next
    INDEX
    Explanations

    words related to registration processes or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of registration

    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
    aneers
    -0.86
    stars
    -0.72
     Pear
    -0.70
    ealous
    -0.70
    ghan
    -0.69
    ore
    -0.69
     Woods
    -0.69
    hei
    -0.65
    acious
    -0.65
    æĦ
    -0.65
    POSITIVE LOGITS
     registration
    3.73
     registrations
    2.99
     Registration
    2.88
    Registration
    2.56
     registering
    2.21
     regist
    2.10
     register
    1.96
     registered
    1.89
     Regist
    1.85
    istration
    1.79
    Activations Density 0.019%

    No Known Activations