© 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. 3500
    Prev
    Next
    INDEX
    Explanations

    words related to movement across a physical boundary or line

    oai_token-act-pair · gpt-3.5-turbo

    references to borders and crossings

    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
    thood
    -0.82
    RESULTS
    -0.81
    housing
    -0.74
    Vs
    -0.74
    naissance
    -0.73
    finding
    -0.73
    ONS
    -0.71
    NG
    -0.70
    ummies
    -0.70
    ISON
    -0.69
    POSITIVE LOGITS
     river
    1.16
     Atlantic
    1.09
     pond
    1.01
     border
    0.99
     creek
    0.98
     street
    0.98
     ocean
    0.97
     threshold
    0.97
     lake
    0.95
     plains
    0.94
    Activations Density 0.080%

    No Known Activations