© 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. 7105
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal disputes and labor organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of National League teams and related abbreviations in the context of baseball

    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
    flies
    -0.95
    idate
    -0.87
    icles
    -0.79
    iasis
    -0.79
    shake
    -0.75
    hift
    -0.75
    strap
    -0.74
    lain
    -0.73
    rette
    -0.73
    ku
    -0.72
    POSITIVE LOGITS
    RB
    0.85
    NL
    0.82
    TP
    0.80
    ibrary
    0.80
    umber
    0.76
    emonic
    0.74
    IJ
    0.74
    FG
    0.73
     penn
    0.71
    onge
    0.71
    Activations Density 0.012%

    No Known Activations