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. 21374
    Prev
    Next
    INDEX
    Explanations

    names or mentions of the name "Anton"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Anton" related to significant figures or individuals

    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
     Wii
    -0.76
    drive
    -0.69
     widget
    -0.67
     widgets
    -0.65
    ting
    -0.62
    ogs
    -0.61
     WD
    -0.61
    HI
    -0.60
     drive
    -0.60
     drill
    -0.59
    POSITIVE LOGITS
     Anton
    3.83
    Ant
    1.49
     Alexand
    1.31
     Antonio
    1.31
     Andreas
    1.28
     Viktor
    1.25
     Leon
    1.25
     Ant
    1.24
    Alexander
    1.22
     Alexander
    1.21
    Activations Density 0.013%

    No Known Activations