© 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. 16076
    Prev
    Next
    INDEX
    Explanations

    words related to disappearance or removal

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gone" and its variations, indicating loss or absence

    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
     glim
    -0.69
     Deity
    -0.63
    aire
    -0.63
    advertisement
    -0.63
    eers
    -0.63
    role
    -0.61
    Sol
    -0.60
     Cosponsors
    -0.59
    ums
    -0.58
    ussen
    -0.58
    POSITIVE LOGITS
     overboard
    0.93
     forever
    0.87
     unnoticed
    0.85
     bye
    0.81
     viral
    0.81
     limp
    0.75
     extinct
    0.73
     rogue
    0.72
     silent
    0.69
     Bye
    0.68
    Activations Density 0.030%

    No Known Activations