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. 8-RES-JB
    6. 3457
    Prev
    Next
    INDEX
    Explanations

    phrases expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating speculation, belief, or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.78
    ciating
    -0.67
     Himself
    -0.66
    Lear
    -0.62
    sac
    -0.61
    ository
    -0.60
    washer
    -0.59
     demo
    -0.59
    ļéĨĴ
    -0.58
     Delicious
    -0.58
    POSITIVE LOGITS
     sclerosis
    0.67
     errone
    0.67
     spoilers
    0.66
     incorrectly
    0.66
     blame
    0.65
    ael
    0.63
     underestimate
    0.62
     impeachment
    0.60
     benches
    0.60
     exaggeration
    0.60
    Activations Density 0.188%

    No Known Activations