© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 216
    Prev
    Next
    INDEX
    Explanations

    terms related to the term "Business"

    oai_token-act-pair · gpt-3.5-turbo

    references to business-related topics or entities

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

    No Comments

    Negative Logits
    adow
    -0.71
    cki
    -0.64
    adows
    -0.64
     glances
    -0.63
    onso
    -0.62
    uable
    -0.61
    stanbul
    -0.61
     tv
    -0.61
    stals
    -0.60
     thence
    -0.60
    POSITIVE LOGITS
    INESS
    1.09
    Desk
    0.96
     Machines
    0.88
     Insider
    0.87
    Business
    0.87
    business
    0.85
    woman
    0.83
    Week
    0.83
    es
    0.83
    week
    0.80
    Activations Density 0.020%

    No Known Activations