© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6706
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, identified as Adams

    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
     phyl
    -0.78
    sector
    -0.74
     sector
    -0.68
    rawdownloadcloneembedreportprint
    -0.68
     shr
    -0.67
     loader
    -0.66
     ë
    -0.65
     Slovenia
    -0.65
    omb
    -0.64
     lit
    -0.63
    POSITIVE LOGITS
     Adams
    3.91
    Adams
    3.05
     Hancock
    1.61
     Daniels
    1.29
     Jefferson
    1.26
     Armstrong
    1.25
     Dickinson
    1.24
     Bates
    1.21
     Jennings
    1.21
     Williamson
    1.17
    Activations Density 0.014%

    No Known Activations