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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16921
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal and political concepts such as openness, solidarity, and power distribution

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social issues and collective challenges

    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
     NYC
    -0.79
     Costco
    -0.66
     CDC
    -0.66
     Colorado
    -0.64
     FDA
    -0.62
    )).
    -0.62
     Purdue
    -0.62
     Florida
    -0.61
     FAA
    -0.61
     DEA
    -0.61
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    0.75
    ppings
    0.69
    estyle
    0.63
    keleton
    0.63
    icrobial
    0.61
    imet
    0.60
    ãĤ¦ãĤ¹
    0.60
    ranging
    0.59
    avering
    0.58
    pecially
    0.58
    Activations Density 1.003%

    No Known Activations