© 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. 9-RES-JB
    11. 5430
    Prev
    Next
    INDEX
    Explanations

    words related to geographical landscapes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental features and landscapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     omission
    -0.87
     Hitman
    -0.82
     translator
    -0.77
     reprim
    -0.71
     taunt
    -0.70
     Quote
    -0.70
     memo
    -0.70
     handwriting
    -0.69
     humility
    -0.69
     Reply
    -0.69
    POSITIVE LOGITS
     corridors
    1.09
    osphere
    1.09
    ranean
    1.07
    vironments
    1.05
    anse
    1.03
     rivers
    1.03
     farmland
    1.02
    accessible
    1.02
    ridges
    1.01
    insula
    1.01
    Activations Density 0.283%

    No Known Activations