Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 31
    Prev
    Next
    INDEX
    Explanations

    the name "Kal" followed by various suffixes or contexts

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific individual named Kal

    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
    ãĥ¼ãĥĨãĤ£
    -0.84
    åij
    -0.69
     ageing
    -0.64
    ãģį
    -0.62
     halftime
    -0.62
     suff
    -0.61
     broken
    -0.60
     depreciation
    -0.60
     accounting
    -0.60
     mature
    -0.59
    POSITIVE LOGITS
    amaz
    1.43
    adesh
    1.36
    arov
    1.06
    inda
    1.04
    endar
    1.04
    adin
    1.03
    insky
    1.01
    endars
    0.99
    vin
    0.99
    ivas
    0.99
    Activations Density 0.011%

    No Known Activations