© 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. 8-RES-JB
    11. 18620
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement through space or locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "through"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isted
    -0.82
    abet
    -0.77
    CTV
    -0.74
    IST
    -0.72
    Ring
    -0.69
    UTH
    -0.68
    added
    -0.65
    aires
    -0.64
    ettle
    -0.63
    OST
    -0.63
    POSITIVE LOGITS
     waivers
    0.78
    )=(
    0.72
     clenched
    0.67
     intersections
    0.67
     obscurity
    0.66
    agall
    0.65
     veins
    0.65
     town
    0.64
     hoops
    0.64
     bushes
    0.61
    Activations Density 0.051%

    No Known Activations