© 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. 22222
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Zhang and Liu

    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
     Ajax
    -0.87
    Philadelphia
    -0.83
     Philly
    -0.81
     Delaware
    -0.78
     Bucks
    -0.77
    Plugin
    -0.75
     sod
    -0.74
     Jersey
    -0.74
     ESP
    -0.74
     Nebraska
    -0.73
    POSITIVE LOGITS
     Zhang
    2.99
     Liu
    2.97
     Zhou
    2.91
     Huang
    2.82
     Wang
    2.80
     Jiang
    2.78
     Zhao
    2.75
     Yuan
    2.71
     Zheng
    2.68
     Xu
    2.68
    Activations Density 0.063%

    No Known Activations