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. 11-RES-JB
    6. 22966
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to legal issues and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Croatian
    -0.93
     MX
    -0.85
     Sinai
    -0.83
    stanbul
    -0.81
     Serbian
    -0.79
     Istanbul
    -0.79
     Kos
    -0.79
     Gim
    -0.79
     Yugoslav
    -0.79
     Croatia
    -0.79
    POSITIVE LOGITS
     Warren
    2.67
    Warren
    2.54
     Elizabeth
    1.52
    Elizabeth
    1.35
     Buffett
    1.22
     Dodd
    1.21
     Berkshire
    1.20
     Massachusetts
    1.12
     Vanguard
    1.06
     Sanders
    1.05
    Activations Density 0.163%

    No Known Activations