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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17961
    Prev
    Next
    INDEX
    Explanations

    questions and prompts for information

    oai_token-act-pair · gpt-3.5-turbo

    questions and interrogative sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igans
    -0.83
    atten
    -0.71
    oling
    -0.68
    oche
    -0.67
    pointers
    -0.67
    iple
    -0.66
    rawdownloadcloneembedreportprint
    -0.66
    ryu
    -0.64
    zin
    -0.64
    tin
    -0.63
    POSITIVE LOGITS
     Explain
    0.85
     What
    0.76
     Close
    0.75
     Why
    0.75
     Previous
    0.75
     Would
    0.73
     How
    0.73
     Does
    0.73
     Who
    0.71
     Disability
    0.70
    Activations Density 0.047%

    No Known Activations