© 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. 10-RES-JB
    11. 16708
    Prev
    Next
    INDEX
    Explanations

    new information or opportunities

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating prior accessibility or availability of resources or opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Errors
    -0.79
     inacc
    -0.75
    cens
    -0.74
     Conclusion
    -0.72
     severity
    -0.69
     inconsistency
    -0.68
     incorrect
    -0.68
     correctness
    -0.68
     Modes
    -0.67
     Error
    -0.66
    POSITIVE LOGITS
     subsidized
    1.20
     subsid
    1.18
     renting
    1.17
     leasing
    1.14
     financed
    1.13
     hire
    1.11
     sponsoring
    1.10
     partnerships
    1.09
     donated
    1.08
     financing
    1.07
    Activations Density 0.973%

    No Known Activations