© 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. 13564
    Prev
    Next
    INDEX
    Explanations

    directional indicators, specifically cardinal directions like north, south, east, and west

    oai_token-act-pair · gpt-3.5-turbo

    directional indicators related to movement and location

    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
     "$:/
    -0.73
    ucha
    -0.69
    ocrats
    -0.68
    ulous
    -0.67
    aints
    -0.66
    wcsstore
    -0.65
    ellation
    -0.64
    URES
    -0.62
    ags
    -0.59
    pty
    -0.59
    POSITIVE LOGITS
    ward
    1.39
    wards
    1.10
    west
    1.04
    bound
    0.92
    side
    0.87
    outheast
    0.86
     latitude
    0.85
    western
    0.84
    wind
    0.84
    WARD
    0.84
    Activations Density 0.063%

    No Known Activations