© 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. 3-RES-JB
    11. 6452
    Prev
    Next
    INDEX
    Explanations

    information or news-related content indicated by the word "MORE" in the text

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "MORE" indicating additional content or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bows
    -0.86
    stood
    -0.85
    ades
    -0.75
    arist
    -0.74
    liest
    -0.74
    vet
    -0.74
    apers
    -0.70
    aper
    -0.69
    ffe
    -0.69
     Springer
    -0.69
    POSITIVE LOGITS
     ado
    0.90
    MORE
    0.88
     VIDEOS
    0.87
     MORE
    0.87
     than
    0.85
     IMAGES
    0.85
     Than
    0.85
    htaking
    0.82
    agascar
    0.79
     WATCHED
    0.79
    Activations Density 0.020%

    No Known Activations