© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 6587
    Prev
    Next
    INDEX
    Explanations

    references to body positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its context related to locations or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.86
    ividual
    -0.80
    lance
    -0.73
    hire
    -0.72
    eful
    -0.71
    illac
    -0.69
    iac
    -0.69
    Bloom
    -0.68
    uls
    -0.67
    lessly
    -0.67
    POSITIVE LOGITS
     pavement
    1.38
     sidewalk
    1.37
     floor
    1.37
     ground
    1.28
     sofa
    1.25
     porch
    1.24
     couch
    1.24
     ledge
    1.22
     doorstep
    1.19
     balcony
    1.17
    Activations Density 0.131%

    No Known Activations