© 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. 1768
    Prev
    Next
    INDEX
    Explanations

    quotes and statements from various sources

    oai_token-act-pair · gpt-3.5-turbo

    references to communication or statements made by individuals, especially in interviews or social media

    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
     perfected
    -0.54
    hovah
    -0.51
     Doe
    -0.51
    ographically
    -0.50
     prest
    -0.49
     imported
    -0.48
    soDeliveryDate
    -0.48
    Exper
    -0.48
     Voy
    -0.46
     beneficiaries
    -0.46
    POSITIVE LOGITS
     remarks
    0.72
     sarcast
    0.64
    Bloomberg
    0.63
     apologised
    0.63
     yesterday
    0.62
     thanking
    0.61
     keynote
    0.60
     acknow
    0.59
     clar
    0.58
     Wednesday
    0.58
    Activations Density 0.787%

    No Known Activations