© 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. 4-RES-JB
    11. 20231
    Prev
    Next
    INDEX
    Explanations

    instances where the word "Both" appears in the text

    oai_token-act-pair · gpt-3.5-turbo

    statements involving the word "both" indicating shared circumstances or actions

    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
    ugu
    -0.86
    udic
    -0.75
    uez
    -0.74
    uable
    -0.71
    opian
    -0.70
    ça
    -0.70
    empl
    -0.70
    istle
    -0.69
    achment
    -0.69
    ¨
    -0.68
    POSITIVE LOGITS
     sexes
    1.31
     sides
    1.14
     halves
    1.14
     genders
    1.13
     parties
    0.88
     sets
    0.83
    ocating
    0.75
     kinds
    0.72
     ends
    0.71
     houses
    0.71
    Activations Density 0.046%

    No Known Activations