© 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. 7-RES-JB
    11. 20790
    Prev
    Next
    INDEX
    Explanations

    decisions or actions being made or taken

    oai_token-act-pair · gpt-3.5-turbo

    statements related 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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dig
    -0.80
    aeus
    -0.70
    ritical
    -0.68
    heres
    -0.67
    ugs
    -0.66
    naissance
    -0.66
    nces
    -0.65
    osponsors
    -0.65
    Versions
    -0.64
    riet
    -0.62
    POSITIVE LOGITS
     decisions
    1.08
     decision
    1.02
     deciding
    0.98
     priorit
    0.88
     deliber
    0.86
     whether
    0.83
     advis
    0.80
     Decision
    0.80
     unanimously
    0.80
     wisely
    0.78
    Activations Density 0.218%

    No Known Activations