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. 8-RES-JB
    6. 466
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, focusing on names starting with 'K'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Krist" and its variations or derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lance
    -0.86
    olia
    -0.81
    avorite
    -0.73
    ascript
    -0.72
    allo
    -0.69
     fung
    -0.69
    isite
    -0.68
    ishable
    -0.68
    ongo
    -0.66
     predec
    -0.66
    POSITIVE LOGITS
     Ernst
    0.83
     Stras
    0.81
     Ves
    0.80
     Friedrich
    0.79
     Vand
    0.78
     Klopp
    0.78
    bos
    0.77
     Fischer
    0.77
     Vers
    0.77
     Ober
    0.76
    Activations Density 0.139%

    No Known Activations