Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22805
    Prev
    Next
    INDEX
    Explanations

    images or visual descriptions indicated with the word "pictured"

    oai_token-act-pair · gpt-3.5-turbo

    references to images and their locations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     increment
    -0.72
     dependency
    -0.62
     Distribution
    -0.62
     ±
    -0.61
     reasonable
    -0.61
     appreci
    -0.61
     lin
    -0.61
     extension
    -0.59
     dependence
    -0.59
     fatigue
    -0.59
    POSITIVE LOGITS
    pictured
    3.87
    above
    1.66
    shown
    1.66
    below
    1.40
     pictured
    1.36
    left
    1.24
    SPONSORED
    1.21
    sic
    1.19
    seen
    1.13
    Scroll
    1.11
    Activations Density 0.021%

    No Known Activations