© 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. 9361
    Prev
    Next
    INDEX
    Explanations

    words related to risk or risky actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to risk

    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
    upon
    -0.91
    Nap
    -0.81
    innie
    -0.78
    ann
    -0.78
    oin
    -0.76
    ental
    -0.75
    bert
    -0.75
    through
    -0.74
    elf
    -0.74
    onne
    -0.73
    POSITIVE LOGITS
     risky
    1.19
     gamble
    1.07
     gamb
    0.97
     bets
    0.89
     risks
    0.84
     risk
    0.83
     proposition
    0.82
     sounding
    0.78
     undermin
    0.76
     maneuvers
    0.74
    Activations Density 0.011%

    No Known Activations