© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 11464
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to a place called Boca

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Boca" and variations or related terms

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

    No Comments

    Negative Logits
    boxes
    -0.77
    culosis
    -0.76
    schild
    -0.74
    cases
    -0.72
    box
    -0.70
    sg
    -0.70
    ROR
    -0.69
    NESS
    -0.69
    MENTS
    -0.67
    owed
    -0.64
    POSITIVE LOGITS
    oca
    1.07
     starch
    1.00
    uthor
    0.94
    Cola
    0.87
    ciating
    0.80
     Lumpur
    0.79
    zyk
    0.76
    zyme
    0.75
    ourt
    0.75
    ignt
    0.74
    Activations Density 0.013%

    No Known Activations