© 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. 6-RES-JB
    11. 16863
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographical locations, especially areas with the word "wood" in their names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various locations or entities associated with "wood"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ional
    -0.79
    Magikarp
    -0.72
     polar
    -0.71
    oresc
    -0.70
    orsche
    -0.68
     Uriel
    -0.66
    olar
    -0.65
     Mehran
    -0.62
     xen
    -0.62
     kindred
    -0.60
    POSITIVE LOGITS
    mere
    1.00
    vale
    0.98
    hurst
    0.92
     Springs
    0.91
    wood
    0.90
     Preferred
    0.87
    leigh
    0.86
    stock
    0.86
    working
    0.83
    seed
    0.83
    Activations Density 0.017%

    No Known Activations