© 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. 9-RES-JB
    11. 7418
    Prev
    Next
    INDEX
    Explanations

    Biblical references and quotes

    oai_token-act-pair · gpt-3.5-turbo

    references to notable quotes or texts

    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
     hosting
    -0.75
     stoked
    -0.74
     paralyzed
    -0.72
    blocking
    -0.67
     targeted
    -0.67
     pledged
    -0.66
     mascara
    -0.66
     betting
    -0.66
     sunscreen
    -0.64
    awed
    -0.64
    POSITIVE LOGITS
     supra
    1.40
     pp
    1.26
     pg
    1.21
     vol
    1.06
     Ibid
    1.05
     Encyclopedia
    1.05
     §
    1.03
     footnote
    1.01
     Appendix
    1.01
    20439
    0.98
    Activations Density 0.288%

    No Known Activations