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. 817
    Prev
    Next
    INDEX
    Explanations

    mentions of things that are official or require some kind of formal registration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "registered" in various contexts

    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
     embr
    -0.79
    jen
    -0.77
     Ashes
    -0.76
     wisdom
    -0.73
    phil
    -0.72
    nature
    -0.71
    dest
    -0.70
    thora
    -0.69
     ape
    -0.67
    alysis
    -0.66
    POSITIVE LOGITS
     registered
    3.84
     Registered
    2.58
    registered
    2.39
     registering
    2.16
    Registered
    2.05
     register
    1.98
     registration
    1.92
     registrations
    1.91
     regist
    1.74
     licensed
    1.56
    Activations Density 0.007%

    No Known Activations