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. 17673
    Prev
    Next
    INDEX
    Explanations

    various instances of the word "kind"

    oai_token-act-pair · gpt-3.5-turbo

    references to different types or categories of things

    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
     Annotations
    -0.72
    wm
    -0.69
    arthed
    -0.64
    Prem
    -0.63
     During
    -0.61
    ten
    -0.61
    ¶
    -0.61
    istan
    -0.61
     Submit
    -0.60
    acher
    -0.60
    POSITIVE LOGITS
     kind
    3.59
     sort
    2.98
     kinds
    2.35
     kinda
    2.21
    kind
    2.09
     sorts
    2.04
     type
    2.00
     Kind
    1.83
    Kind
    1.74
    sort
    1.52
    Activations Density 0.021%

    No Known Activations