© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14471
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms of the word "its."

    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
    roup
    -0.87
    tch
    -0.85
    Alert
    -0.77
    wine
    -0.74
    eva
    -0.73
    ©¶æ¥µ
    -0.72
    Newsletter
    -0.69
    ticket
    -0.69
    GROUP
    -0.68
    tsy
    -0.67
    POSITIVE LOGITS
     implications
    1.27
     usefulness
    1.26
     significance
    1.23
     importance
    1.22
     adherents
    1.22
     relevance
    1.20
     effectiveness
    1.19
     ramifications
    1.17
     effects
    1.17
     origins
    1.17
    Activations Density 0.108%

    No Known Activations