© 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. 7-RES-JB
    11. 13999
    Prev
    Next
    INDEX
    Explanations

    mentions of catastrophic events or overwhelming situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "delve."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rity
    -0.69
    forth
    -0.69
    OLOGY
    -0.69
     Fields
    -0.65
    YA
    -0.65
     Methods
    -0.64
    é¾įå¥ij士
    -0.64
    LESS
    -0.63
    SHIP
    -0.63
    ral
    -0.62
    POSITIVE LOGITS
    uxe
    1.19
    uded
    1.04
    ivery
    0.97
    ving
    0.96
     Toro
    0.95
    ights
    0.89
    uge
    0.87
    uding
    0.85
    ivered
    0.85
    upe
    0.85
    Activations Density 0.016%

    No Known Activations