© 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. 10-RES-JB
    11. 9982
    Prev
    Next
    INDEX
    Explanations

    information related to the geographical origin of plant and animal species

    oai_token-act-pair · gpt-3.5-turbo

    references to species native to specific regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.92
    Tickets
    -0.84
    RT
    -0.83
    Mayor
    -0.83
    TRUMP
    -0.73
    Transfer
    -0.72
    Uber
    -0.70
    operator
    -0.70
    Opening
    -0.70
    Charges
    -0.70
    POSITIVE LOGITS
     southeastern
    1.47
     northeastern
    1.41
     northwestern
    1.39
     Madagascar
    1.38
     southwestern
    1.37
     Tasmania
    1.35
     forests
    1.34
     Yellowstone
    1.32
     tropical
    1.31
     Appalach
    1.30
    Activations Density 0.360%

    No Known Activations