© 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. 2-RES-JB
    11. 12495
    Prev
    Next
    INDEX
    Explanations

    phrases related to business deals and agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to agreements or arrangements in a business context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Naz
    -0.66
    IENT
    -0.65
    ATIONAL
    -0.65
    \\\\\\\\\\\\\\\\
    -0.64
    ãĥŁ
    -0.63
    ATH
    -0.62
    Technology
    -0.61
    Mill
    -0.60
    OST
    -0.60
     Gren
    -0.60
    POSITIVE LOGITS
    hips
    1.48
    ettings
    1.32
    poons
    1.19
    ometimes
    1.18
    uggest
    1.18
    hare
    1.12
    uits
    1.02
    chool
    1.01
    afety
    1.01
    hops
    0.99
    Activations Density 0.060%

    No Known Activations