© 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. 6-RES-JB
    11. 17524
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical thinking and self-awareness

    oai_token-act-pair · gpt-3.5-turbo

    instances of cognitive processing or awareness in the context of individual thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Appears
    -0.58
    erto
    -0.57
     Sov
    -0.57
     Reincarn
    -0.55
    udo
    -0.54
    issance
    -0.54
     Tycoon
    -0.54
     PTS
    -0.53
    soever
    -0.52
     namesake
    -0.52
    POSITIVE LOGITS
    ĸļ
    0.79
    »Ĵ
    0.68
    paren
    0.62
    arton
    0.62
    reader
    0.61
     VIDEOS
    0.58
    picture
    0.58
    Sel
    0.58
    HTML
    0.57
    alde
    0.57
    Activations Density 1.761%

    No Known Activations