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. 12-RES-JB
    6. 14714
    Prev
    Next
    INDEX
    Explanations

    biochemical terms related to enzyme activity and chemical compounds

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    medical terms and scientific nomenclature related to cellular and biochemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advising
    -0.72
     chuck
    -0.70
     lik
    -0.66
     reserved
    -0.64
     Osw
    -0.63
     Galile
    -0.62
     flock
    -0.62
     dub
    -0.61
     amen
    -0.59
     trump
    -0.59
    POSITIVE LOGITS
    ulf
    1.27
    cler
    1.19
    omal
    1.07
    ynthesis
    1.05
    ucc
    1.03
    odium
    1.02
    perm
    1.02
    clerosis
    0.98
    orb
    0.96
    olute
    0.96
    Activations Density 0.074%

    No Known Activations