© 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. 11134
    Prev
    Next
    INDEX
    Explanations

    the word "No" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "no" indicating denial or refusal

    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
    endish
    -0.64
    worn
    -0.63
    FML
    -0.63
    erala
    -0.61
    tyard
    -0.60
    tnc
    -0.60
    leaning
    -0.59
    ËĪ
    -0.58
    Roaming
    -0.58
    istani
    -0.57
    POSITIVE LOGITS
    oooooooo
    1.09
    oooo
    1.07
    oooooooooooooooo
    1.04
     worries
    0.99
     matter
    0.96
    ooo
    0.92
     thanks
    0.91
     sir
    0.91
     clue
    0.90
     kidding
    0.90
    Activations Density 0.037%

    No Known Activations