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. 10-RES-JB
    6. 2456
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and government policies

    oai_token-act-pair · gpt-3.5-turbo
    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
    onica
    -0.79
    tale
    -0.76
    hedon
    -0.75
    ONY
    -0.71
     Ars
    -0.69
    VALUE
    -0.69
    ÑĮ
    -0.67
     Mayhem
    -0.67
     Guilty
    -0.67
    beh
    -0.67
    POSITIVE LOGITS
     defund
    1.31
     abolish
    1.31
     privat
    1.30
     abol
    1.25
     overhaul
    1.24
     repeal
    1.22
     repealing
    1.21
     eliminate
    1.19
     curtail
    1.15
     eliminating
    1.12
    Activations Density 0.367%

    No Known Activations