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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 14593
    Prev
    Next
    INDEX
    Explanations

    words related to risk and potential danger

    oai_token-act-pair · gpt-3.5-turbo

    terms related to risk and gamble

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

    No Comments

    Negative Logits
    Nap
    -0.88
    anooga
    -0.86
    parts
    -0.83
    entity
    -0.76
    author
    -0.72
    riot
    -0.71
    ĺħ
    -0.71
    shall
    -0.71
    ¼
    -0.68
    population
    -0.67
    POSITIVE LOGITS
     gamble
    1.33
     risky
    1.14
     gamb
    1.10
     bets
    0.96
     betting
    0.79
     risks
    0.77
    cffff
    0.75
     maneuver
    0.74
     plunge
    0.73
     Woods
    0.72
    Activations Density 0.026%

    No Known Activations