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. 2-RES-JB
    6. 4874
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "registry"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of registries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.85
    bian
    -0.70
    verty
    -0.67
    Kind
    -0.66
    furt
    -0.66
     Cheap
    -0.65
    anguages
    -0.65
    fall
    -0.63
    Fine
    -0.62
    opot
    -0.62
    POSITIVE LOGITS
     registry
    1.36
     Registry
    0.91
     regist
    0.79
     bom
    0.75
     hive
    0.75
     database
    0.73
     trademark
    0.71
     linkage
    0.70
     registration
    0.69
    istry
    0.68
    Activations Density 0.008%

    No Known Activations