© 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. 7-RES-JB
    11. 23061
    Prev
    Next
    INDEX
    Explanations

    locations mentioned in street names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific roads and their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pes
    -0.81
    irements
    -0.75
    ropolitan
    -0.73
    arians
    -0.72
    arian
    -0.71
     franc
    -0.68
     hor
    -0.65
     reproduce
    -0.64
     reel
    -0.63
    atorial
    -0.63
    POSITIVE LOGITS
    side
    0.92
    stead
    0.88
     Rd
    0.86
     Racer
    0.85
     Roads
    0.82
    course
    0.81
    street
    0.80
    kill
    0.79
    ways
    0.77
     Road
    0.76
    Activations Density 0.020%

    No Known Activations