© 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. 7-RES-JB
    11. 20680
    Prev
    Next
    INDEX
    Explanations

    references to related topics or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    content related to supplementary material or associated content, possibly used for further exploration or understanding

    oai_token-act-pair · gpt-3.5-turbo
    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
    UGE
    -0.79
    »Ĵ
    -0.78
    arer
    -0.77
    ainted
    -0.74
    esan
    -0.72
    atur
    -0.70
    acers
    -0.67
    elfth
    -0.67
    gmail
    -0.66
    ample
    -0.65
    POSITIVE LOGITS
     Stories
    1.01
     Links
    0.90
     Articles
    0.88
     Content
    0.85
     Factors
    0.83
     Coverage
    0.82
     articles
    0.82
     Occupations
    0.79
     Videos
    0.79
     Advertisement
    0.78
    Activations Density 0.027%

    No Known Activations