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. 11-RES-JB
    6. 19739
    Prev
    Next
    INDEX
    Explanations

    the name "Karl" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Kar" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aloud
    -0.69
    CRIP
    -0.65
     forth
    -0.62
    åij
    -0.61
     spread
    -0.61
     Merrill
    -0.60
     Furious
    -0.60
     BLM
    -0.59
     compliment
    -0.59
     Unic
    -0.59
    POSITIVE LOGITS
    amaz
    1.20
    zai
    1.18
    isma
    1.17
    acan
    1.14
    sten
    1.14
    olina
    1.13
    imov
    1.06
    adj
    1.05
    imi
    1.03
    olyn
    0.97
    Activations Density 0.022%

    No Known Activations