© 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. 9907
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions or purposes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intent or purpose

    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
    writ
    -0.68
    wrote
    -0.65
     Steps
    -0.61
     millenn
    -0.61
    prints
    -0.59
    standing
    -0.59
     Printed
    -0.59
     Binary
    -0.58
    Offline
    -0.57
     Debor
    -0.57
    POSITIVE LOGITS
     appease
    1.43
     alleviate
    1.26
     lessen
    1.22
     relieve
    1.20
     maximize
    1.18
     satisfy
    1.18
     avoid
    1.16
     bolster
    1.16
     intimidate
    1.15
     discourage
    1.15
    Activations Density 0.204%

    No Known Activations