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. 0-RES-JB
    6. 9351
    Prev
    Next
    INDEX
    Explanations

    proper names with the surname "berger"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Berger."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sockets
    -0.70
     socket
    -0.65
     Sind
    -0.64
     glam
    -0.63
     res
    -0.59
     long
    -0.59
     rept
    -0.58
     temple
    -0.57
     mem
    -0.57
     roles
    -0.56
    POSITIVE LOGITS
    berger
    4.46
    berg
    1.72
    baugh
    1.64
    burg
    1.53
    bach
    1.48
    baum
    1.46
    meier
    1.43
    bart
    1.39
    heimer
    1.37
    meyer
    1.36
    Activations Density 0.008%

    No Known Activations