Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 23102
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to engineering and technology

    oai_token-act-pair · gpt-3.5-turbo

    technical processes involving scientific research and innovation

    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
     Scholar
    -0.82
    ibliography
    -0.78
     Conclusion
    -0.73
     Reasons
    -0.71
    Conclusion
    -0.70
    Mania
    -0.68
     Overall
    -0.66
     Unsure
    -0.66
     Occupations
    -0.66
    ghazi
    -0.65
    POSITIVE LOGITS
     electrodes
    1.49
     magnets
    1.34
     lasers
    1.30
     sensors
    1.23
     electrom
    1.16
     electromagnetic
    1.16
     microscopic
    1.15
     nanop
    1.14
     atoms
    1.14
     infrared
    1.13
    Activations Density 0.525%

    No Known Activations