© 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. 2-RES-JB
    6. 1764
    Prev
    Next
    INDEX
    Explanations

    references to corporate or business-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "business."

    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
     Nielsen
    -0.75
    aired
    -0.73
    ussen
    -0.69
    netflix
    -0.69
    anche
    -0.68
    alys
    -0.63
    arity
    -0.63
    gger
    -0.62
    onso
    -0.60
    âĢ¢âĢ¢
    -0.60
    POSITIVE LOGITS
    INESS
    1.04
    business
    0.92
     mogul
    0.92
     dealings
    0.91
     establishments
    0.90
     owners
    0.85
     empire
    0.84
     enterprises
    0.84
    woman
    0.84
    Desk
    0.81
    Activations Density 0.034%

    No Known Activations