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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 6994
    Prev
    Next
    INDEX
    Explanations

    references to legal and political contexts, along with discussion of personal and academic use

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to various purposes for using substances or resources, particularly in legal, medical, and commercial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    etheless
    -1.09
    former
    -0.80
    jri
    -0.76
    ixties
    -0.71
    usted
    -0.69
    ãĤ´ãĥ³
    -0.68
    wait
    -0.68
    undrum
    -0.68
    quez
    -0.67
    antine
    -0.67
    POSITIVE LOGITS
     purposes
    2.16
     reasons
    1.83
     purpose
    1.45
     uses
    1.26
     sake
    1.17
     use
    1.14
     occasions
    1.13
     reason
    1.13
     Reasons
    1.11
     benefit
    1.09
    Activations Density 0.249%

    No Known Activations