© 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 EvalsExportsinterp-engineNEWAPI 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. 24347
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms and actions, such as arrests and charges

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "to be" in different forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     transplant
    -0.68
     multif
    -0.66
    iots
    -0.66
     compan
    -0.63
     congr
    -0.61
     whiff
    -0.60
     graft
    -0.60
     certific
    -0.59
     nets
    -0.59
    ãģĤ
    -0.59
    POSITIVE LOGITS
    ufact
    0.91
    rius
    0.85
    ESA
    0.81
    rium
    0.71
    ensical
    0.71
    rial
    0.67
    incial
    0.65
    icable
    0.65
    ogyn
    0.65
     Zot
    0.64
    Activations Density 0.108%

    No Known Activations