© 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. 11-RES-JB
    11. 16410
    Prev
    Next
    INDEX
    Explanations

    geographical locations, specifically those referring to directions or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic directions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scissors
    -0.76
     Logo
    -0.74
     Swordsman
    -0.74
     Creator
    -0.72
     Anonymous
    -0.71
     Dynamics
    -0.71
     Calculator
    -0.70
     Proced
    -0.68
     Question
    -0.68
     Measure
    -0.68
    POSITIVE LOGITS
    east
    1.88
    west
    1.77
    facing
    1.58
    western
    1.55
    central
    1.55
    south
    1.55
    north
    1.36
    Eastern
    1.28
    East
    1.24
    West
    1.20
    Activations Density 0.022%

    No Known Activations