© 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. 24329
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial and business transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the private sector and its various industries

    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
    ãĥ¯ãĥ³
    -0.82
    ر
    -0.74
    alos
    -0.73
    onday
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
     Ragnarok
    -0.67
     Yamato
    -0.65
    orically
    -0.63
    risome
    -0.62
    ĪĴ
    -0.62
    POSITIVE LOGITS
     oath
    0.75
    ancies
    0.71
     contractors
    0.71
     owned
    0.67
     partnerships
    0.67
     portfolios
    0.66
     corporations
    0.65
     Holdings
    0.64
     assistants
    0.64
     pronouns
    0.62
    Activations Density 0.303%

    No Known Activations