© 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. 19677
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specialized terms related to various fields or individuals

    oai_token-act-pair · gpt-3.5-turbo

    elements related to the concept of a collective or community

    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
    ruary
    -0.67
     Admir
    -0.66
    advertisement
    -0.65
     Swordsman
    -0.62
     Unlock
    -0.60
    atform
    -0.59
    cellence
    -0.58
     Scythe
    -0.57
    owship
    -0.56
     Zot
    -0.55
    POSITIVE LOGITS
    士
    0.83
    allah
    0.72
    owski
    0.71
    oult
    0.70
    oki
    0.69
    chal
    0.69
    opic
    0.69
    ovi
    0.67
    д
    0.66
    Ó
    0.66
    Activations Density 0.225%

    No Known Activations