© 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. 14792
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completion or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating completion or the end of a process

    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
    unia
    -0.72
    vice
    -0.70
    weeney
    -0.65
    onal
    -0.61
     streng
    -0.61
    ©¶æ
    -0.61
    obal
    -0.61
    ispers
    -0.60
    arlane
    -0.58
     singled
    -0.57
    POSITIVE LOGITS
     Congratulations
    0.96
    !
    0.93
    !.
    0.80
    !:
    0.78
    !,
    0.77
    !!!
    0.74
    !'
    0.73
     :-)
    0.72
    ãĢĤ
    0.70
    Congratulations
    0.69
    Activations Density 0.284%

    No Known Activations