© 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 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. 9-RES-JB
    11. 20853
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to events or actions coming to a conclusion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "end" and its variations, indicating conclusions or terminations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    hee
    -0.68
     broom
    -0.61
    esome
    -0.61
    onne
    -0.57
     Parables
    -0.56
     rooft
    -0.55
     reused
    -0.55
    minecraft
    -0.55
    icipated
    -0.54
     squared
    -0.54
    POSITIVE LOGITS
     prematurely
    1.12
    angering
    1.09
     abruptly
    1.07
     tragically
    0.96
    owment
    0.87
     peacefully
    0.86
    angers
    0.84
    ear
    0.81
    orses
    0.79
    eared
    0.78
    Activations Density 0.046%

    No Known Activations