© 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. 10-RES-JB
    11. 14034
    Prev
    Next
    INDEX
    Explanations

    phrases starting with the word "Well"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "Well."

    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
    omore
    -0.66
    ËĪ
    -0.65
    ¥ŀ
    -0.64
    illary
    -0.63
    rift
    -0.63
    cffff
    -0.63
    avorite
    -0.62
    ilater
    -0.60
    aded
    -0.58
    ©¶æ¥µ
    -0.58
    POSITIVE LOGITS
     yeah
    1.01
     hello
    0.94
    ington
    0.94
     guess
    0.92
     congratulations
    0.91
    esley
    0.90
     prest
    0.87
     luckily
    0.84
    adays
    0.83
    tons
    0.83
    Activations Density 0.029%

    No Known Activations