© 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. 15874
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of 'outside' or external environment

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'outside'

    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
    ony
    -0.82
    enegger
    -0.79
    anwhile
    -0.75
    orah
    -0.75
    arrell
    -0.74
    hered
    -0.71
    onder
    -0.70
    oran
    -0.69
    ndra
    -0.67
    riages
    -0.66
    POSITIVE LOGITS
     observer
    0.95
     world
    0.79
     observers
    0.77
     linebackers
    0.75
    most
    0.74
     linebacker
    0.73
     hemisphere
    0.73
    world
    0.72
     Outs
    0.71
     appearance
    0.70
    Activations Density 0.054%

    No Known Activations