© 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. 1-RES-JB
    11. 2659
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly "Erik" and "Kraken."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Erik" and references to the "Kraken" group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    birth
    -0.80
    body
    -0.78
    wide
    -0.75
    roads
    -0.73
    cock
    -0.73
    path
    -0.72
    yards
    -0.67
    ãģĤ
    -0.67
    Food
    -0.67
    talking
    -0.65
    POSITIVE LOGITS
     Erik
    1.32
    kson
    1.01
    ildo
    1.01
     Spo
    0.98
     Wem
    0.97
    sson
    0.90
     Bry
    0.88
    ansson
    0.87
     Larson
    0.86
    lund
    0.86
    Activations Density 0.004%

    No Known Activations