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. 11-RES-JB
    6. 15369
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases indicating personal accomplishment or achievements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     volunte
    -0.71
     quir
    -0.68
     satell
    -0.67
     millenn
    -0.66
     rall
    -0.64
     distribut
    -0.63
     enthusi
    -0.60
     disag
    -0.59
     wider
    -0.59
     incendiary
    -0.58
    POSITIVE LOGITS
     Your
    1.92
    Your
    1.78
     You
    1.72
    your
    1.61
    You
    1.49
     Congratulations
    1.45
     YOUR
    1.44
     Yourself
    1.38
    you
    1.28
     your
    1.24
    Activations Density 0.432%

    No Known Activations