© 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. 7-RES-JB
    11. 5015
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles of persons

    oai_token-act-pair · gpt-3.5-turbo

    specific names and references related to medical or wellness topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     boo
    -0.44
    wcs
    -0.44
    CPU
    -0.40
     broom
    -0.37
     downed
    -0.37
     whipping
    -0.36
     basket
    -0.36
     unheard
    -0.36
     choke
    -0.35
     upset
    -0.35
    POSITIVE LOGITS
    ¶
    0.50
     Conclusion
    0.44
     concludes
    0.44
    leness
    0.42
     Liang
    0.41
    endix
    0.41
    CONCLUS
    0.40
     ³³
    0.40
     recommends
    0.39
    hao
    0.39
    Activations Density 2.834%

    No Known Activations