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. 19922
    Prev
    Next
    INDEX
    Explanations

    specialized equipment and terms related to expertise

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specialization and specialized knowledge

    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
    =-=-=-=-=-=-=-=-
    -0.84
    iPhone
    -0.76
    alter
    -0.72
    Jesus
    -0.72
    runner
    -0.72
    á
    -0.71
    down
    -0.69
    Jane
    -0.69
     Truman
    -0.68
    ————————————————
    -0.68
    POSITIVE LOGITS
     specialized
    1.28
    ategory
    0.95
     minded
    0.90
     specialization
    0.89
     proble
    0.88
     servicing
    0.84
     specialize
    0.83
     cryptoc
    0.83
     satell
    0.81
    rete
    0.80
    Activations Density 0.006%

    No Known Activations