© 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. 7757
    Prev
    Next
    INDEX
    Explanations

    towns or place names, specifically searching for "Clare"

    oai_token-act-pair · gpt-3.5-turbo

    names of people and places

    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
    akable
    -0.78
     sacrific
    -0.77
    aphael
    -0.74
    agonists
    -0.73
    ilater
    -0.71
    efully
    -0.70
    vana
    -0.67
    @@@@@@@@
    -0.65
    ternity
    -0.64
    orical
    -0.63
    POSITIVE LOGITS
     County
    1.38
     Borough
    1.28
     Township
    1.19
     residents
    1.16
     resident
    1.14
    shire
    1.13
     Parish
    1.13
     Province
    1.08
     Mayor
    1.08
     municipality
    1.05
    Activations Density 0.493%

    No Known Activations