© 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. 0-RES-JB
    11. 5199
    Prev
    Next
    INDEX
    Explanations

    references to physical locations, particularly buildings like halls

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the color green and references to venues or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beat
    -0.84
    Beat
    -0.70
     repe
    -0.70
     beaten
    -0.68
     leve
    -0.66
     Juventus
    -0.66
     pinned
    -0.66
    comb
    -0.64
     beat
    -0.63
     bluff
    -0.63
    POSITIVE LOGITS
     halls
    1.61
    reen
    1.58
     corridors
    1.52
    kson
    1.41
     nic
    1.38
     Guide
    1.22
     Halls
    1.07
    rigan
    1.00
    riers
    1.00
    raph
    0.91
    Activations Density 0.045%

    No Known Activations