© 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. 4001
    Prev
    Next
    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific political figures, particularly members of the Gandhi family

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Concord
    -0.88
    foundland
    -0.80
     Scotia
    -0.80
    ĨĴ
    -0.71
    apple
    -0.70
     psychiatrists
    -0.68
    ASED
    -0.66
     psychiatrist
    -0.66
    tower
    -0.66
     Scientology
    -0.64
    POSITIVE LOGITS
     Gandhi
    1.12
     Rahul
    1.09
     Sharma
    0.96
     Modi
    0.80
    igans
    0.78
     Singh
    0.78
    jit
    0.77
     Patel
    0.77
    Rah
    0.75
     Rah
    0.74
    Activations Density 0.007%

    No Known Activations