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. 10-RES-JB
    6. 3762
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a preference for one option over another

    oai_token-act-pair · gpt-3.5-turbo

    comparisons emphasizing preference or choice over alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.69
    ppa
    -0.63
    hemy
    -0.63
    endum
    -0.61
    otti
    -0.61
    rats
    -0.60
    inka
    -0.59
    ORY
    -0.58
    tsky
    -0.58
     Kard
    -0.57
    POSITIVE LOGITS
     than
    1.56
    than
    1.26
     Than
    0.97
     then
    0.81
    Th
    0.67
    Else
    0.67
     TH
    0.64
     compared
    0.63
     resembling
    0.63
     suited
    0.63
    Activations Density 0.016%

    No Known Activations