© 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. 1-RES-JB
    11. 16880
    Prev
    Next
    INDEX
    Explanations

    mention of threats to species survival

    oai_token-act-pair · gpt-3.5-turbo

    terms related to extinction and endangered species

    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
    annis
    -0.76
    maid
    -0.75
    leading
    -0.71
    weeney
    -0.71
    ker
    -0.67
    rollers
    -0.66
    wik
    -0.65
    anooga
    -0.65
    NC
    -0.62
    rooms
    -0.62
    POSITIVE LOGITS
     extinction
    1.30
     extinct
    1.03
     proble
    0.93
     Clicker
    0.91
    ãĤ¼ãĤ¦ãĤ¹
    0.88
    inctions
    0.86
     unlaw
    0.86
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.86
     beetle
    0.83
    inction
    0.81
    Activations Density 0.007%

    No Known Activations