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. 2-RES-JB
    6. 22804
    Prev
    Next
    INDEX
    Explanations

    words related to beliefs and convictions

    oai_token-act-pair · gpt-3.5-turbo

    references to beliefs or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.73
    apeake
    -0.72
    nice
    -0.70
    bye
    -0.69
    avis
    -0.68
     Sieg
    -0.68
    nova
    -0.66
    yna
    -0.66
     Amen
    -0.65
    hma
    -0.65
    POSITIVE LOGITS
     belief
    0.99
    ieve
    0.90
    fulness
    0.90
     beliefs
    0.88
    fully
    0.80
    ually
    0.79
    itious
    0.77
     faith
    0.76
     conviction
    0.76
     disbelief
    0.76
    Activations Density 0.020%

    No Known Activations