© 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. 17273
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning or wondering about reasons or causes

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions and expressions of confusion or questioning

    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
    urst
    -0.85
    Fra
    -0.76
    furt
    -0.71
    FAQ
    -0.69
    ãĤ£
    -0.68
    Ö¼
    -0.62
    ãĤ´
    -0.61
    flies
    -0.61
     subjective
    -0.60
     doubtful
    -0.60
    POSITIVE LOGITS
     sooner
    1.06
     mention
    0.87
    hin
    0.75
     prosecute
    0.74
     include
    0.71
    itia
    0.70
     pursue
    0.69
     inherit
    0.69
     publish
    0.69
     earlier
    0.67
    Activations Density 0.117%

    No Known Activations