© 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. 8614
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and regulations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases emphasizing connections or relationships

    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
    ãĥģ
    -0.82
    pmwiki
    -0.67
    brow
    -0.64
    onte
    -0.64
    ãĥ³ãĤ¸
    -0.62
    stage
    -0.62
    ãĥī
    -0.61
    ãĥ¼ãĥ
    -0.61
    ãĤ°
    -0.61
    apeake
    -0.59
    POSITIVE LOGITS
     secondly
    1.44
     hence
    1.33
     consequently
    1.28
     furthermore
    1.23
     moreover
    1.17
     therefore
    1.16
     thus
    1.13
     whilst
    1.06
     luckily
    1.06
     fortunately
    0.97
    Activations Density 0.417%

    No Known Activations