© 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. 7-RES-JB
    11. 4934
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or suggestion

    oai_token-act-pair · gpt-3.5-turbo

    instances of speculative or uncertain thinking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    earch
    -0.73
    mons
    -0.64
    eenth
    -0.61
     [-
    -0.61
    andise
    -0.60
    licts
    -0.59
    lings
    -0.59
    ibel
    -0.58
     GEAR
    -0.58
    ume
    -0.58
    POSITIVE LOGITS
     someday
    0.99
     somew
    0.90
     misunder
    0.89
     luck
    0.73
    Äĩ
    0.72
     inadvert
    0.72
     wiser
    0.71
     underest
    0.71
     overlooked
    0.70
    rosso
    0.69
    Activations Density 0.193%

    No Known Activations