© 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. 17365
    Prev
    Next
    INDEX
    Explanations

    key entities or components within a given context or system

    oai_token-act-pair · gpt-3.5-turbo

    the word "key" used in various contexts to denote important elements or factors

    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
     Chatt
    -0.74
     Tsukuyomi
    -0.74
     Carbuncle
    -0.73
     Horses
    -0.71
     Bett
    -0.66
    ews
    -0.65
    AUT
    -0.65
    uthor
    -0.64
     PHOTO
    -0.64
     Mile
    -0.63
    POSITIVE LOGITS
    stroke
    1.11
    stone
    1.09
    stro
    0.99
    */(
    0.95
    stones
    0.93
    wcs
    0.90
    role
    0.89
    hole
    0.88
     key
    0.88
    ring
    0.85
    Activations Density 0.017%

    No Known Activations