© 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. 12328
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or entities, particularly focusing on events or topics related to sports teams, surveillance methods, and online content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Bournemouth" and variations of it

    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
     program
    -0.70
     abort
    -0.63
     sync
    -0.63
     matrix
    -0.63
     gar
    -0.63
     Marc
    -0.62
     ROM
    -0.62
     Project
    -0.61
     --
    -0.61
     fragment
    -0.61
    POSITIVE LOGITS
    emouth
    5.46
    ottenham
    1.35
    racuse
    1.34
    CHQ
    1.34
    swick
    1.33
    elong
    1.21
    vier
    1.20
    ipeg
    1.15
    zeb
    1.14
    raltar
    1.13
    Activations Density 0.021%

    No Known Activations