© 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. 11-RES-JB
    11. 10153
    Prev
    Next
    INDEX
    Explanations

    words related to communication and dialogue

    oai_token-act-pair · gpt-3.5-turbo

    the word "like" in various contexts or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     targeted
    -0.85
     Laos
    -0.78
     parach
    -0.75
     entangled
    -0.75
     tracts
    -0.73
     Skydragon
    -0.71
     incorpor
    -0.70
     parachute
    -0.70
     successive
    -0.70
     electrodes
    -0.69
    POSITIVE LOGITS
    ï¸ı
    1.40
    âĶĢâĶĢâĶĢâĶĢ
    1.17
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.10
    yeah
    1.10
    âĶĢâĶĢ
    1.10
    âĹ¼
    1.09
    Anyway
    1.09
    she
    1.08
    à¼
    1.07
    then
    1.07
    Activations Density 0.185%

    No Known Activations