© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19796
    Prev
    Next
    INDEX
    Explanations

    words related to paper, including "paperwork."

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of paper products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ostic
    -0.79
    CVE
    -0.77
    artment
    -0.73
    alez
    -0.72
    akening
    -0.70
    aren
    -0.70
    ivals
    -0.69
    Xi
    -0.68
    ^^^^
    -0.67
    ostics
    -0.67
    POSITIVE LOGITS
     towels
    1.09
    clip
    1.09
    Paper
    1.07
     towel
    0.97
    clips
    0.89
     Paper
    0.86
    paper
    0.81
    maid
    0.81
    flies
    0.80
    pee
    0.79
    Activations Density 0.022%

    No Known Activations