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. 8036
    Prev
    Next
    INDEX
    Explanations

    numeric information such as numbers and statistics

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to significant events and their consequences

    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
     varies
    -0.65
     differently
    -0.65
     depends
    -0.62
    yip
    -0.61
    oat
    -0.61
    ophen
    -0.61
     ?)
    -0.60
    ?).
    -0.57
     unfocusedRange
    -0.57
    ?),
    -0.56
    POSITIVE LOGITS
     culminating
    1.00
     effortlessly
    0.85
     undet
    0.80
     totaling
    0.79
     boasting
    0.79
    .[
    0.77
     earning
    0.76
    .
    0.74
     thanks
    0.73
     enabling
    0.70
    Activations Density 0.690%

    No Known Activations