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. 15452
    Prev
    Next
    INDEX
    Explanations

    instances where the statement or action is contradictory

    oai_token-act-pair · gpt-3.5-turbo

    the word "but", indicating contrasting statements

    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
    edu
    -0.78
    gie
    -0.70
    oire
    -0.69
    uto
    -0.68
    ampa
    -0.67
    esc
    -0.67
    ige
    -0.65
    sky
    -0.65
    tnc
    -0.63
    Times
    -0.63
    POSITIVE LOGITS
     alas
    1.14
     nevertheless
    1.13
     nonetheless
    1.12
     lacks
    0.95
     fortunately
    0.95
     retains
    0.94
     lacked
    0.92
     ignores
    0.91
     luckily
    0.91
    chery
    0.90
    Activations Density 0.176%

    No Known Activations