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. 10-RES-JB
    6. 22104
    Prev
    Next
    INDEX
    Explanations

    the word "kind" followed by an adjective

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "kind" used to describe various categories or types of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ZI
    -0.66
     VIDEOS
    -0.64
    foreseen
    -0.64
    sbm
    -0.63
     Bots
    -0.63
    UNCH
    -0.62
     Kod
    -0.60
     Clarkson
    -0.60
     Dover
    -0.60
     Nadu
    -0.59
    POSITIVE LOGITS
    hearted
    1.24
    ling
    1.15
    er
    1.10
    lier
    1.08
    liness
    1.07
    nesses
    0.99
    ness
    0.96
    est
    0.95
    led
    0.93
    les
    0.89
    Activations Density 0.032%

    No Known Activations