© 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. 1-RES-JB
    11. 3629
    Prev
    Next
    INDEX
    Explanations

    locations or geographic areas

    oai_token-act-pair · gpt-3.5-turbo

    references to densely populated regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.73
    Enough
    -0.71
    SB
    -0.71
    raid
    -0.69
    etheus
    -0.68
    Tro
    -0.67
    Fac
    -0.67
    Maximum
    -0.64
    ATH
    -0.64
    Prev
    -0.63
    POSITIVE LOGITS
     areas
    1.44
     area
    1.06
     Areas
    1.06
     regions
    0.91
    area
    0.83
    manship
    0.76
     sectors
    0.76
     locations
    0.76
     zones
    0.75
    pots
    0.75
    Activations Density 0.014%

    No Known Activations