© 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. 11585
    Prev
    Next
    INDEX
    Explanations

    The neuron seems to activate for sentences starting with "I know I", with varying levels of certainty and emotional tones

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal knowledge or experiences

    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
    BuyableInstoreAndOnline
    -0.74
    etheus
    -0.63
     Âł Âł
    -0.60
     Cancel
    -0.60
    opes
    -0.59
    rex
    -0.58
     resume
    -0.58
    anship
    -0.57
    arantine
    -0.57
    eworthy
    -0.56
    POSITIVE LOGITS
    )</
    0.72
    sb
    0.71
    PLA
    0.70
     firsthand
    0.67
    CLA
    0.64
    stadt
    0.63
     plenty
    0.61
    anza
    0.61
    ById
    0.60
    %);
    0.59
    Activations Density 0.271%

    No Known Activations