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. 21912
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names starting with "Kar"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Kar"

    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
    CRIP
    -0.76
    IBLE
    -0.74
    åij
    -0.70
     NX
    -0.70
    ãģį
    -0.69
     wip
    -0.65
     agents
    -0.65
     Yankee
    -0.64
     sunny
    -0.64
     Merrill
    -0.63
    POSITIVE LOGITS
    amaz
    1.20
    sten
    1.12
    zai
    1.11
    olyn
    1.06
    thal
    1.05
    olina
    1.05
    isma
    1.00
    acan
    0.99
    negie
    0.98
    onel
    0.98
    Activations Density 0.019%

    No Known Activations