© 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. 10-RES-JB
    11. 12902
    Prev
    Next
    INDEX
    Explanations

    phrases related to captions underneath images

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of image captions or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bats
    -0.75
     accur
    -0.64
    fing
    -0.60
    merce
    -0.60
    terday
    -0.60
     mosqu
    -0.59
    ionage
    -0.56
    stress
    -0.56
     traged
    -0.56
     fortun
    -0.56
    POSITIVE LOGITS
    ËĪ
    0.94
     Prev
    0.75
     Courtesy
    0.72
    img
    0.70
    actionDate
    0.70
     Image
    0.69
     Images
    0.69
     Picture
    0.69
    src
    0.67
     WATCHED
    0.66
    Activations Density 0.008%

    No Known Activations