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. 0-RES-JB
    6. 6049
    Prev
    Next
    INDEX
    Explanations

    instances of something being officially recognized or declared

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "officially" and similar terms indicating formal declarations or confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reading
    -0.67
    cit
    -0.66
    feed
    -0.65
     potency
    -0.65
    ilus
    -0.62
    asion
    -0.61
     fixation
    -0.61
     Patient
    -0.60
     disproportionate
    -0.60
     Dickinson
    -0.59
    POSITIVE LOGITS
     officially
    3.37
     formally
    2.45
     official
    1.71
     Offic
    1.60
    official
    1.56
     definitively
    1.49
     publicly
    1.47
     technically
    1.46
    offic
    1.43
    Official
    1.36
    Activations Density 0.019%

    No Known Activations