© 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 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. 7-RES-JB
    11. 1880
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of business models

    oai_token-act-pair · gpt-3.5-turbo

    references to business models and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gger
    -0.68
    arity
    -0.63
     Janeiro
    -0.62
    netflix
    -0.62
    aired
    -0.61
    ifer
    -0.61
    blank
    -0.60
    emonic
    -0.60
    adoes
    -0.60
    stals
    -0.59
    POSITIVE LOGITS
     dealings
    0.98
    INESS
    0.98
    Desk
    0.94
     owners
    0.93
     mogul
    0.91
     ventures
    0.87
    woman
    0.84
     empire
    0.83
     owner
    0.79
    people
    0.79
    Activations Density 0.043%

    No Known Activations