© 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. 7-RES-JB
    11. 23892
    Prev
    Next
    INDEX
    Explanations

    phrases related to carbon dioxide levels in the atmosphere

    oai_token-act-pair · gpt-3.5-turbo

    mentions of carbon dioxide (CO2)

    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
    lihood
    -0.93
    soever
    -0.78
     Brach
    -0.75
     NOTICE
    -0.73
    ifications
    -0.72
    nik
    -0.71
    istical
    -0.69
     Pry
    -0.68
    ions
    -0.66
    saf
    -0.65
    POSITIVE LOGITS
    OPER
    0.96
    INC
    0.90
    VO
    0.89
    VEN
    0.86
    FF
    0.85
    LL
    0.84
    VERT
    0.83
    CO
    0.82
    CHR
    0.79
    ST
    0.79
    Activations Density 0.016%

    No Known Activations