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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2372
    Prev
    Next
    INDEX
    Explanations

    proper nouns (specific names) related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    the name "Chen" in various contexts

    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
    =#
    -0.72
    [_
    -0.66
    Flag
    -0.66
     derby
    -0.65
     warp
    -0.64
     FM
    -0.63
    rift
    -0.63
     flair
    -0.60
    flag
    -0.60
     boot
    -0.60
    POSITIVE LOGITS
     Chen
    3.65
     Xu
    1.62
     Huang
    1.59
     Wong
    1.58
     Zhang
    1.53
     Liang
    1.53
     Cheng
    1.50
     Zhao
    1.48
     Shen
    1.47
     Zhou
    1.46
    Activations Density 0.022%

    No Known Activations