© 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. 18563
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "Well, " and potentially followed by contrasting or additional information

    oai_token-act-pair · gpt-3.5-turbo

    the word "well" and variations of punctuation, particularly commas

    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
    keyes
    -0.72
    Winged
    -0.71
    minster
    -0.71
    ealous
    -0.70
    è»
    -0.70
    ebted
    -0.69
    adem
    -0.66
    âĵĺ
    -0.65
    İĭ
    -0.65
    pering
    -0.64
    POSITIVE LOGITS
     yeah
    1.25
     guess
    1.17
     maybe
    1.16
     uh
    1.09
     luckily
    1.07
     fortunately
    1.04
     yes
    1.04
     hello
    1.00
     congr
    0.99
     okay
    0.96
    Activations Density 0.086%

    No Known Activations