© 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. 10-RES-JB
    11. 10120
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a contrasting or surprising element in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that contrast or introduce conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.78
    ãĥİ
    -0.78
    urated
    -0.77
    ãĤ¼ãĤ¦ãĤ¹
    -0.76
    esp
    -0.76
    tein
    -0.75
    ãĤ¡
    -0.73
    ufact
    -0.72
    ãĤ¦ãĤ¹
    -0.72
    ãĤ¿
    -0.70
    POSITIVE LOGITS
     somehow
    1.19
     despite
    0.99
     strangely
    0.96
     nonetheless
    0.95
     again
    0.94
     another
    0.89
     nevertheless
    0.87
     inexpl
    0.84
     mirac
    0.82
     somew
    0.82
    Activations Density 0.039%

    No Known Activations