© 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. 11-RES-JB
    11. 22159
    Prev
    Next
    INDEX
    Explanations

    sections describing physical movement and action sequences

    oai_token-act-pair · gpt-3.5-turbo

    actions involving pursuit and conflict

    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
    Tea
    -0.72
     Topics
    -0.69
     Recipes
    -0.68
     renovations
    -0.66
    Reviewer
    -0.65
    ocolate
    -0.65
    Anonymous
    -0.65
     questionnaire
    -0.64
     Ethnic
    -0.64
     Discuss
    -0.63
    POSITIVE LOGITS
     staggered
    1.20
     sprint
    1.19
     dodged
    1.19
     leapt
    1.13
     collided
    1.12
     crou
    1.10
     instinctively
    1.08
     tumble
    1.06
     lun
    1.04
     lung
    1.04
    Activations Density 0.480%

    No Known Activations