© 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. 8-RES-JB
    11. 23401
    Prev
    Next
    INDEX
    Explanations

    mentions of tropical environments

    oai_token-act-pair · gpt-3.5-turbo

    references to tropical environments and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mellon
    -0.89
    brance
    -0.86
    viation
    -0.81
    usable
    -0.81
    avering
    -0.81
    umbn
    -0.80
    baugh
    -0.79
    edin
    -0.79
    Merit
    -0.76
    adr
    -0.76
    POSITIVE LOGITS
     forests
    0.89
     fruits
    0.88
     islands
    0.88
     jungle
    0.87
     tropical
    0.87
     climates
    0.84
     deforestation
    0.84
     forest
    0.83
     humid
    0.81
     cycl
    0.80
    Activations Density 0.050%

    No Known Activations