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. 10-RES-JB
    6. 10868
    Prev
    Next
    INDEX
    Explanations

    academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to academic institutions and their affiliations

    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
    20439
    -0.84
    netflix
    -0.84
    maid
    -0.78
     sqor
    -0.74
    nation
    -0.72
    ername
    -0.71
    é»Ĵ
    -0.70
    Downloadha
    -0.70
    externalActionCode
    -0.70
    76561
    -0.69
    POSITIVE LOGITS
     Technology
    1.24
     Excellence
    1.10
     Medicine
    1.09
     Sciences
    1.07
     Physics
    1.06
     Science
    1.06
     Photography
    1.06
     Journalism
    1.01
     Arts
    1.01
     Applied
    1.01
    Activations Density 0.069%

    No Known Activations