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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 13030
    Prev
    Next
    INDEX
    Explanations

    references to carbon dioxide (CO2) levels and their impacts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of carbon dioxide (CO2) and its levels or concentrations

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

    No Comments

    Negative Logits
    ©¶æ
    -0.75
     Cantor
    -0.71
     Pengu
    -0.69
    awaru
    -0.67
    custom
    -0.65
    Ĥª
    -0.65
     Jem
    -0.64
    ĻĤ
    -0.64
     srfAttach
    -0.64
     Rak
    -0.64
    POSITIVE LOGITS
     emissions
    0.96
     dioxide
    0.92
    ucl
    0.84
     poisoning
    0.83
     resin
    0.82
    ioxide
    0.80
     pollution
    0.80
     deposition
    0.79
     contamination
    0.78
     depletion
    0.77
    Activations Density 0.027%

    No Known Activations