© 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. 8-RES-JB
    11. 7055
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or inquiries about a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning authenticity or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĿ
    -0.70
    letter
    -0.69
     Nurs
    -0.66
    irez
    -0.63
    wagon
    -0.62
    ulas
    -0.60
    illac
    -0.60
    checks
    -0.59
    bye
    -0.59
    sectional
    -0.58
    POSITIVE LOGITS
     why
    1.10
     whether
    0.98
     WHY
    0.87
     how
    0.86
     justify
    0.76
    why
    0.73
    whether
    0.73
    yx
    0.71
     whereabouts
    0.71
    wing
    0.69
    Activations Density 0.049%

    No Known Activations