© 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. 20102
    Prev
    Next
    INDEX
    Explanations

    terms related to making important choices or judgements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant decisions or choices

    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
    vae
    -0.74
    ingers
    -0.70
    rake
    -0.68
    hemat
    -0.66
    outh
    -0.66
    rawling
    -0.64
    ammers
    -0.64
     Dak
    -0.62
    amen
    -0.62
     Smile
    -0.62
    POSITIVE LOGITS
     decision
    1.09
     decisions
    1.03
     makers
    0.83
     stance
    0.80
    DragonMagazine
    0.79
     warr
    0.74
     Decision
    0.73
     calculus
    0.72
     choices
    0.71
     decides
    0.71
    Activations Density 0.032%

    No Known Activations