© 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. 1-RES-JB
    6. 23193
    Prev
    Next
    INDEX
    Explanations

    keywords related to carbon dioxide levels and atmospheric conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to carbon dioxide (CO2) throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.86
     Brach
    -0.85
    ion
    -0.79
    saf
    -0.79
    ions
    -0.77
    oku
    -0.70
    nik
    -0.70
    nir
    -0.69
    soever
    -0.67
    =\"
    -0.66
    POSITIVE LOGITS
     CO
    1.10
    CO
    1.01
     Colo
    0.83
    OPER
    0.83
    VO
    0.83
    CHR
    0.79
    KE
    0.74
    STON
    0.70
    ffer
    0.69
     emissions
    0.69
    Activations Density 0.004%

    No Known Activations