© 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. 8-RES-JB
    11. 8227
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their distribution in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of policies and government programs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gobl
    -0.83
     mosqu
    -0.75
     satell
    -0.72
    cano
    -0.72
     spor
    -0.72
    à¦
    -0.69
     resil
    -0.68
     carbohyd
    -0.66
     conductor
    -0.66
     stray
    -0.65
    POSITIVE LOGITS
     Critics
    1.20
     Ideally
    1.17
     Specifically
    1.14
     Whereas
    1.11
     Accordingly
    1.10
     Such
    1.09
     Otherwise
    1.08
     Meanwhile
    1.07
     Ultimately
    1.06
    Critics
    1.03
    Activations Density 0.495%

    No Known Activations