© 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. 2-RES-JB
    11. 8392
    Prev
    Next
    INDEX
    Explanations

    instances of the word "yes" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    affirmative responses or expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ojure
    -0.80
    Merit
    -0.79
    lets
    -0.76
    bage
    -0.75
    Offline
    -0.74
    RAW
    -0.72
    rarily
    -0.72
     externalToEVAOnly
    -0.71
    DragonMagazine
    -0.70
    ributed
    -0.69
    POSITIVE LOGITS
    terday
    1.37
     yes
    1.06
    etheless
    0.88
     sir
    0.87
     YES
    0.79
     matter
    0.73
     Yes
    0.73
     sure
    0.72
     parole
    0.70
     stranger
    0.69
    Activations Density 0.008%

    No Known Activations