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. 12-RES-JB
    6. 15239
    Prev
    Next
    INDEX
    Explanations

    legal and political terms related to court proceedings and government actions

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

    legal and regulatory terminology related to medical marijuana and cannabis legislation

    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
    ãĥİ
    -0.82
    tics
    -0.79
    anium
    -0.78
    oeuv
    -0.76
    ãĥ¼ãĥĨãĤ£
    -0.74
    ãĤ¨ãĥ«
    -0.69
    ãĥĬ
    -0.69
    ¯
    -0.68
    ãĥīãĥ©ãĤ´ãĥ³
    -0.68
    Firstly
    -0.67
    POSITIVE LOGITS
     legislatures
    1.23
     lawmakers
    1.17
     legislators
    1.12
     Gov
    1.10
     advocates
    1.05
     Congress
    1.04
     Attorney
    0.97
     mayors
    0.95
     regulators
    0.95
     Governor
    0.94
    Activations Density 0.517%

    No Known Activations