© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14382
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making processes or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pse
    -0.80
     menace
    -0.72
     Reporting
    -0.70
    unte
    -0.68
     Offense
    -0.67
    à
    -0.67
    Versions
    -0.66
     Schwe
    -0.64
     Detected
    -0.63
    ãĥķãĤ¡
    -0.63
    POSITIVE LOGITS
     decisions
    1.29
     decision
    1.19
     Decision
    0.95
     unanimous
    0.89
     weighing
    0.88
     regretted
    0.88
    amic
    0.86
     overr
    0.85
     influenced
    0.85
     choices
    0.85
    Activations Density 0.169%

    No Known Activations