© 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. 0-RES-JB
    11. 23353
    Prev
    Next
    INDEX
    Explanations

    references to the historical figure Stalin

    oai_token-act-pair · gpt-3.5-turbo

    references to Joseph Stalin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [+]
    -0.86
     brace
    -0.81
     Emirates
    -0.74
     hop
    -0.72
    bj
    -0.71
     Mic
    -0.70
     beads
    -0.69
     Dive
    -0.68
     bead
    -0.67
     Meter
    -0.66
    POSITIVE LOGITS
     Stalin
    3.90
     Trotsky
    2.36
     Lenin
    2.13
    Lenin
    1.92
     Mao
    1.79
     Truman
    1.49
     Bolshevik
    1.48
     Hitler
    1.46
     Auschwitz
    1.45
     Bolshe
    1.43
    Activations Density 0.034%

    No Known Activations