Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 6764
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the physical act of 'gutting' something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "gut" and related emotional or physical reactions

    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
    hips
    -0.79
    BuyableInstoreAndOnline
    -0.75
    hift
    -0.73
     Stephenson
    -0.72
     Aad
    -0.68
     Chains
    -0.68
     reconc
    -0.66
     Standing
    -0.65
    WithNo
    -0.65
     Kingdoms
    -0.65
    POSITIVE LOGITS
    ted
    1.23
    ters
    1.12
    ierrez
    1.12
    ting
    1.11
    tered
    1.10
    tering
    1.05
    warts
    0.95
    ãĤ¡
    0.91
    buster
    0.91
    lig
    0.90
    Activations Density 0.022%

    No Known Activations