© 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. 8-RES-JB
    11. 7013
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    mentions of decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anti
    -0.80
    gel
    -0.68
    icas
    -0.67
    amen
    -0.66
    oil
    -0.63
    Versions
    -0.63
    ewitness
    -0.63
    unity
    -0.62
    iday
    -0.61
    ppo
    -0.60
    POSITIVE LOGITS
     decisions
    1.05
     makers
    0.90
     regarding
    0.86
     maker
    0.86
     decision
    0.79
     whether
    0.77
     ACTIONS
    0.77
     concerning
    0.76
     affecting
    0.75
    ptions
    0.74
    Activations Density 0.042%

    No Known Activations