Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3269
    Prev
    Next
    INDEX
    Explanations

    themes related to climate change denial

    oai_token-act-pair · gpt-3.5-turbo

    terms related to climate change denial and associated activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.85
    ij士
    -0.73
    ikuman
    -0.73
    ãĤ¤ãĥĪ
    -0.71
    OHN
    -0.70
    reau
    -0.69
     Marketable
    -0.69
    EStreamFrame
    -0.68
    axter
    -0.68
    OOD
    -0.67
    POSITIVE LOGITS
    iferation
    0.90
    ioxide
    0.68
    ashtra
    0.67
     haze
    0.67
    iland
    0.66
    arians
    0.64
     grav
    0.63
    ifer
    0.63
    ageddon
    0.61
     Grind
    0.61
    Activations Density 0.343%

    No Known Activations