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. 10-RES-JB
    6. 21281
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experiences or feelings

    oai_token-act-pair · gpt-3.5-turbo

    the word "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosyncr
    -0.73
    worthiness
    -0.68
    ð
    -0.68
    izable
    -0.67
     Stability
    -0.66
    ottage
    -0.65
    士
    -0.65
    vernment
    -0.65
     exploits
    -0.64
     Extend
    -0.64
    POSITIVE LOGITS
     wondering
    1.31
     fortunate
    1.26
     lucky
    1.22
     amazed
    1.21
     tempted
    1.20
     expecting
    1.20
     thinking
    1.19
     afraid
    1.17
     surprised
    1.16
     hoping
    1.16
    Activations Density 0.160%

    No Known Activations