© 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. 9-RES-JB
    11. 23449
    Prev
    Next
    INDEX
    Explanations

    locations with references to borders

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" and nearby geographic references

    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
    fully
    -0.85
    ocument
    -0.79
    Anonymous
    -0.77
     alone
    -0.75
    ful
    -0.73
     thereafter
    -0.72
     anew
    -0.69
    aez
    -0.67
    rix
    -0.67
     alike
    -0.67
    POSITIVE LOGITS
     entrance
    1.37
     intersection
    1.14
     entrances
    1.10
     junction
    1.05
     exit
    1.02
     edge
    1.02
     nearest
    0.99
     shores
    0.99
     shore
    0.96
     borders
    0.95
    Activations Density 0.155%

    No Known Activations