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. 3-RES-JB
    6. 22509
    Prev
    Next
    INDEX
    Explanations

    euphemisms

    oai_token-act-pair · gpt-3.5-turbo

    medical terms and concepts relating to conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unpaid
    -0.53
     neut
    -0.52
     pestic
    -0.51
     exha
    -0.45
    iltr
    -0.42
     unlimited
    -0.42
    oresc
    -0.42
     enriched
    -0.42
     reinvest
    -0.42
     carbohyd
    -0.42
    POSITIVE LOGITS
    èĢħ
    0.57
    ttes
    0.55
    hazard
    0.49
    puff
    0.47
    aux
    0.45
    heads
    0.44
    ï¸ı
    0.44
    ught
    0.44
    backer
    0.43
    tale
    0.42
    Activations Density 0.563%

    No Known Activations