© 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. 17431
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic references and citations

    oai_token-act-pair · gpt-3.5-turbo

    references to studies or literature, particularly those citing other works or sources

    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
    Kids
    -0.85
     Kids
    -0.79
     moms
    -0.79
    Cele
    -0.79
     Celeb
    -0.76
     GoPro
    -0.74
     VIP
    -0.73
    Alert
    -0.73
     commercials
    -0.72
     prank
    -0.72
    POSITIVE LOGITS
     methodological
    1.30
     philosophers
    1.16
     normative
    1.11
     conject
    1.11
     empirical
    1.09
     Appendix
    1.07
    ibliography
    1.01
     textual
    1.01
     epist
    1.00
     empir
    1.00
    Activations Density 0.841%

    No Known Activations