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. 10-RES-JB
    6. 19190
    Prev
    Next
    INDEX
    Explanations

    names of people, organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    specific names and entities related to people, organizations, or events

    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
    ;;
    -0.69
     Accessed
    -0.68
    è¦ļéĨĴ
    -0.68
    ORK
    -0.67
    ablished
    -0.64
    ;}
    -0.62
     cd
    -0.61
    uilding
    -0.61
     Purchase
    -0.60
    .;
    -0.59
    POSITIVE LOGITS
     nonetheless
    1.68
     nevertheless
    1.51
     insists
    1.22
     persists
    1.17
     refuses
    1.17
     disagrees
    1.14
     remained
    1.14
     persisted
    1.14
     remains
    1.13
     hasn
    1.12
    Activations Density 0.439%

    No Known Activations