© 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. 8-RES-JB
    11. 20272
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Beijing" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.87
    DOWN
    -0.72
     GEAR
    -0.71
     guiName
    -0.69
    stitial
    -0.65
     impunity
    -0.65
    interrupted
    -0.64
     Zur
    -0.63
    ruciating
    -0.63
    ãģĨ
    -0.62
    POSITIVE LOGITS
    resa
    1.18
    jamin
    1.03
    utsche
    0.94
    levision
    0.91
    odore
    0.89
    icester
    0.88
    vertising
    0.88
    lected
    0.87
    ffield
    0.87
    anmar
    0.86
    Activations Density 0.088%

    No Known Activations