Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4615
    Prev
    Next
    INDEX
    Explanations

    phrases indicating gaining deeper understanding or discussing specific topics

    oai_token-act-pair · gpt-3.5-turbo
    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
    iren
    -0.82
    through
    -0.72
    erity
    -0.72
    eele
    -0.67
    uten
    -0.67
    erence
    -0.65
    aren
    -0.64
    \'
    -0.64
    enegger
    -0.63
    iere
    -0.63
    POSITIVE LOGITS
     specifics
    1.16
     trouble
    1.12
     details
    0.98
     particulars
    0.91
     mischief
    0.91
     detail
    0.90
     politics
    0.87
     discussions
    0.85
     finer
    0.82
     arguments
    0.82
    Activations Density 0.105%

    No Known Activations