© 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. 22542
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial relationships and physical positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe spatial relationships and positioning

    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
    士
    -0.65
    ontent
    -0.59
     rewritten
    -0.57
    failed
    -0.57
     Recession
    -0.57
    zynski
    -0.56
     Comprehensive
    -0.56
    KC
    -0.56
    fail
    -0.56
     Weeks
    -0.55
    POSITIVE LOGITS
     beside
    1.59
     underneath
    1.48
     beneath
    1.41
    behind
    1.41
     below
    1.38
     behind
    1.37
     above
    1.34
     opposite
    1.32
     adjacent
    1.29
    near
    1.28
    Activations Density 0.450%

    No Known Activations