© 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. 8-RES-JB
    11. 5143
    Prev
    Next
    INDEX
    Explanations

    terms related to specific professional roles or contexts

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

    keywords related to technical or informational content, such as programming terms, product names, and legal terms

    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
    ricular
    -0.84
    姫
    -0.79
     Helpful
    -0.76
    etime
    -0.69
    aspers
    -0.64
    verbs
    -0.60
    ega
    -0.59
    pmwiki
    -0.59
    poon
    -0.59
     derog
    -0.59
    POSITIVE LOGITS
    ariat
    0.96
    osphere
    0.90
     itself
    0.88
     wagon
    0.80
    itol
    0.78
    forts
    0.76
    ifies
    0.75
    keepers
    0.72
     debacle
    0.72
     scene
    0.72
    Activations Density 0.461%

    No Known Activations