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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15918
    Prev
    Next
    INDEX
    Explanations

    positively evaluated actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sound decision-making or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oreal
    -0.72
    ļéĨĴ
    -0.70
    anguage
    -0.68
    stories
    -0.68
    icone
    -0.68
    aura
    -0.68
    resy
    -0.67
    ench
    -0.66
    ampions
    -0.66
    ringe
    -0.65
    POSITIVE LOGITS
     decisions
    1.11
     decision
    1.10
     timing
    1.09
     execution
    1.05
     prudent
    1.04
     manoeuv
    0.99
     omission
    0.99
     deliberate
    0.96
     choices
    0.94
     executed
    0.92
    Activations Density 0.687%

    No Known Activations