© 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. 2-RES-JB
    11. 13746
    Prev
    Next
    INDEX
    Explanations

    the adjective "raw" as a descriptor

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "raw" in various contexts

    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
    uyomi
    -0.78
    ŃĶ
    -0.75
    assies
    -0.73
    oppers
    -0.72
     Explain
    -0.71
    merce
    -0.70
    itism
    -0.70
    uate
    -0.70
    akeru
    -0.69
    onial
    -0.69
    POSITIVE LOGITS
    hide
    1.22
     raw
    1.06
    ÃįÃį
    0.95
     sewage
    0.90
    esome
    0.86
    raw
    0.86
    hest
    0.83
     materials
    0.83
    lings
    0.82
    Raw
    0.78
    Activations Density 0.004%

    No Known Activations