© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 5747
    Prev
    Next
    INDEX
    Explanations

    phrases related to reactions or replies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of varied types of responses, particularly in a context related to music or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zot
    -0.71
    BALL
    -0.70
    rome
    -0.69
    fall
    -0.66
    cin
    -0.65
    cutting
    -0.65
     knots
    -0.63
    grave
    -0.62
    ramer
    -0.61
    teenth
    -0.60
    POSITIVE LOGITS
     thereto
    0.94
     response
    0.86
    ivated
    0.83
    aries
    0.81
    naires
    0.80
    iveness
    0.77
     elic
    0.77
    ivation
    0.74
     responses
    0.74
    ively
    0.73
    Activations Density 0.047%

    No Known Activations