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. 4-RES-JB
    6. 15057
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to various fields or professions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to fear, intensity, and emotional depth

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

    No Comments

    Negative Logits
    perate
    -0.59
     Insight
    -0.55
     sidx
    -0.55
    odium
    -0.54
    staking
    -0.53
    osponsors
    -0.51
    untled
    -0.51
     Ago
    -0.50
    âķIJâķIJ
    -0.50
    inarily
    -0.49
    POSITIVE LOGITS
     imaginable
    0.55
    isms
    0.55
     fare
    0.53
     populism
    0.52
     personalities
    0.52
     creations
    0.51
    Semitism
    0.51
     capitalism
    0.51
     polic
    0.51
    oids
    0.51
    Activations Density 1.645%

    No Known Activations