© 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. 2-RES-JB
    6. 11844
    Prev
    Next
    INDEX
    Explanations

    mention of prestigious awards, specifically the Nobel Prize

    oai_token-act-pair · gpt-3.5-turbo

    references to Nobel Prize winners and related awards

    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
    dimension
    -0.65
    tera
    -0.64
    nes
    -0.62
    dest
    -0.62
     CY
    -0.62
     ICE
    -0.61
    alter
    -0.60
    miss
    -0.58
    bang
    -0.58
    yahoo
    -0.58
    POSITIVE LOGITS
     Prize
    1.23
     laureate
    1.18
     laure
    0.96
     Laure
    0.89
     Lect
    0.87
     Medal
    0.85
     Winners
    0.84
     Nobel
    0.83
    Nob
    0.82
     medal
    0.80
    Activations Density 0.013%

    No Known Activations