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. 9-RES-JB
    6. 4363
    Prev
    Next
    INDEX
    Explanations

    web URLs

    oai_token-act-pair · gpt-3.5-turbo

    websites or resources, particularly from government and educational domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pigs
    -0.68
     brackets
    -0.65
     Jungle
    -0.65
     shaving
    -0.65
     landscape
    -0.64
     grounding
    -0.63
     whims
    -0.62
     stacking
    -0.59
     selfies
    -0.59
     rounded
    -0.59
    POSITIVE LOGITS
    org
    1.47
    edu
    1.43
    gov
    1.38
    com
    1.27
    net
    1.20
    biz
    1.14
    ucl
    1.09
    nl
    1.07
    info
    1.06
    nih
    1.06
    Activations Density 0.037%

    No Known Activations