© 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. 11-RES-JB
    11. 7563
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical contact or possession of objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical interaction or possession

    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
    arenthood
    -0.60
     anonymity
    -0.58
    VERTISEMENT
    -0.58
     mund
    -0.58
    WARD
    -0.56
    itability
    -0.56
     Presence
    -0.56
    later
    -0.55
     Nebula
    -0.54
    theless
    -0.54
    POSITIVE LOGITS
     dirty
    1.10
     wet
    0.84
     chopped
    0.79
    dirty
    0.76
     Dirty
    0.71
     pumped
    0.68
     blown
    0.68
     rubbed
    0.67
    ivalent
    0.66
     fucked
    0.66
    Activations Density 0.058%

    No Known Activations