© 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. 16450
    Prev
    Next
    INDEX
    Explanations

    references to sins or sinful behavior

    oai_token-act-pair · gpt-3.5-turbo
    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
     Explorer
    -0.68
     Mechanical
    -0.66
    upp
    -0.64
     Booster
    -0.64
     Train
    -0.64
    rew
    -0.63
    ETF
    -0.63
     Uzbek
    -0.62
    unda
    -0.62
    usters
    -0.61
    POSITIVE LOGITS
     sin
    3.94
     sins
    2.39
    sin
    2.29
     Sin
    2.02
     Sins
    2.00
     sinful
    1.95
    Sin
    1.83
     sinners
    1.83
     transgress
    1.16
     righteousness
    1.15
    Activations Density 0.028%

    No Known Activations