© 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. 19689
    Prev
    Next
    INDEX
    Explanations

    words related to confidence or certainty

    oai_token-act-pair · gpt-3.5-turbo

    expressions of certainty and confidence

    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
    pmwiki
    -0.89
    sites
    -0.77
    Vert
    -0.76
     UCHIJ
    -0.71
    çĦ
    -0.68
    kay
    -0.66
    artifacts
    -0.63
    Mars
    -0.63
     hitch
    -0.62
    bard
    -0.62
    POSITIVE LOGITS
    ially
    1.12
    iated
    0.85
    worthiness
    0.84
    ively
    0.83
    urances
    0.81
    ieth
    0.79
    iably
    0.79
     enough
    0.78
     assurance
    0.72
     confident
    0.70
    Activations Density 0.025%

    No Known Activations