© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 8328
    Prev
    Next
    INDEX
    Explanations

    mentions of actions related to government entities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RANT
    -0.76
    east
    -0.73
    DEN
    -0.72
    sbm
    -0.71
     Rider
    -0.70
    tein
    -0.70
    Magikarp
    -0.69
    CONT
    -0.69
    Brave
    -0.68
    Charge
    -0.66
    POSITIVE LOGITS
    chool
    0.89
     governments
    0.81
     administ
    0.77
    ervatives
    0.74
     subsidized
    0.73
    wide
    0.73
     coffers
    0.72
     funded
    0.72
     bureaucracy
    0.71
    ogun
    0.71
    Activations Density 0.018%

    No Known Activations