© 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. 9332
    Prev
    Next
    INDEX
    Explanations

    phrases related to cordoning off or separating specific areas

    oai_token-act-pair · gpt-3.5-turbo

    references to specific areas, terms related to restrictions or closures, and instances of the word "cull."

    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
    lihood
    -0.64
    DAY
    -0.64
    Americans
    -0.59
    inn
    -0.59
    want
    -0.58
     Abby
    -0.58
    meg
    -0.58
     Nek
    -0.58
    CHA
    -0.58
    piring
    -0.56
    POSITIVE LOGITS
    naire
    1.11
    ordon
    1.11
    éĹĺ
    0.95
    eer
    0.94
    arding
    0.90
    eering
    0.90
    nance
    0.89
    -+-+
    0.87
    edo
    0.80
    ieu
    0.79
    Activations Density 0.021%

    No Known Activations