© 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. 11-RES-JB
    11. 9909
    Prev
    Next
    INDEX
    Explanations

    contrasting relationships or ideas

    oai_token-act-pair · gpt-3.5-turbo

    the word "yet," indicating a contrast or contradiction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¿
    -0.79
    esp
    -0.77
    ãĥİ
    -0.77
    ufact
    -0.76
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
    ãĤ¦ãĤ¹
    -0.73
    ãĤ¨ãĥ«
    -0.73
    ãĤ¡
    -0.73
    /
    -0.72
    tein
    -0.72
    POSITIVE LOGITS
     somehow
    1.17
     despite
    1.07
     again
    0.96
     strangely
    0.93
     another
    0.89
     nonetheless
    0.87
     whenever
    0.82
     somew
    0.81
     inexpl
    0.79
     nevertheless
    0.78
    Activations Density 0.046%

    No Known Activations