© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15698
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and business activities

    oai_token-act-pair · gpt-3.5-turbo

    topics that involve competition, legal issues, or community considerations

    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
    Synopsis
    -0.60
    ','
    -0.54
    ĻĤ
    -0.54
    alg
    -0.53
     Seym
    -0.52
    Tue
    -0.51
    jured
    -0.51
    abases
    -0.51
    Russ
    -0.50
    cknowled
    -0.50
    POSITIVE LOGITS
     becomes
    1.04
     became
    1.02
     outwe
    1.02
     ensued
    1.01
     outweigh
    1.01
     resulted
    0.98
     would
    0.98
     tends
    0.98
     could
    0.97
     coincided
    0.95
    Activations Density 1.050%

    No Known Activations