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. 1-RES-JB
    6. 1387
    Prev
    Next
    INDEX
    Explanations

    references to images or visual representations

    oai_token-act-pair · gpt-3.5-turbo

    instances of visual or artistic representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bern
    -0.83
    bye
    -0.78
    berman
    -0.74
    nder
    -0.74
    ŃĶ
    -0.70
    wood
    -0.70
    ste
    -0.70
    clud
    -0.68
    Chance
    -0.67
    Oak
    -0.67
    POSITIVE LOGITS
     imagery
    1.46
     galleries
    0.95
     visuals
    0.95
     images
    0.87
    ynt
    0.86
     artwork
    0.81
     Imag
    0.81
    irtual
    0.80
     IMAGES
    0.79
     paintings
    0.78
    Activations Density 0.005%

    No Known Activations