© 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. 4-RES-JB
    11. 20789
    Prev
    Next
    INDEX
    Explanations

    locations or areas near specific geographical features or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or geographical features

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

    No Comments

    Negative Logits
    olicy
    -0.72
    thood
    -0.71
     lawy
    -0.71
    manship
    -0.70
    Cash
    -0.68
    nesty
    -0.67
    arians
    -0.66
    ontent
    -0.65
    conom
    -0.65
    icia
    -0.65
    POSITIVE LOGITS
     same
    1.13
     outskirts
    1.08
     latter
    1.04
     smallest
    1.02
     nearest
    1.02
     vicinity
    1.01
     adjoining
    1.01
     dreaded
    1.00
     entire
    0.99
     deepest
    0.99
    Activations Density 0.823%

    No Known Activations