© 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. 10-RES-JB
    11. 16976
    Prev
    Next
    INDEX
    Explanations

    phrases related to proximity or closeness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate proximity or spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORE
    -0.81
    ANS
    -0.76
    rey
    -0.74
    enders
    -0.68
    uct
    -0.67
    ense
    -0.66
    gae
    -0.65
    Meta
    -0.65
    ulous
    -0.63
    hyde
    -0.62
    POSITIVE LOGITS
     bounds
    1.18
     spitting
    1.12
     reach
    1.08
     sight
    0.95
     range
    0.95
     touching
    0.87
     limits
    0.86
     inches
    0.85
     grasp
    0.85
     striking
    0.82
    Activations Density 0.049%

    No Known Activations