© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24281
    Prev
    Next
    INDEX
    Explanations

    instances in text where the concept of having something is expressed

    oai_token-act-pair · gpt-3.5-turbo

    the word "have" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    TG
    -0.70
    oshi
    -0.66
    icking
    -0.64
    oji
    -0.63
    weed
    -0.62
    jam
    -0.61
    igraph
    -0.61
    ourgeois
    -0.60
    patch
    -0.59
     Apart
    -0.58
    POSITIVE LOGITS
     been
    1.22
     begun
    0.98
    been
    0.95
     learnt
    0.93
     become
    0.92
     risen
    0.92
     undergone
    0.91
     gotten
    0.91
     survived
    0.91
     seen
    0.87
    Activations Density 0.235%

    No Known Activations