© 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. 22424
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "end of something."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to endings or conclusions

    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
     WATCHED
    -0.78
    gee
    -0.71
    onne
    -0.70
    itsch
    -0.67
    cko
    -0.67
    pots
    -0.63
    anut
    -0.63
    olulu
    -0.63
    hess
    -0.61
    pub
    -0.61
    POSITIVE LOGITS
     hostilities
    0.91
     Days
    0.85
     usefulness
    0.77
     life
    0.75
    urable
    0.74
     era
    0.73
     civilisation
    0.73
     days
    0.72
     civilization
    0.72
     saga
    0.71
    Activations Density 0.087%

    No Known Activations