Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 22361
    Prev
    Next
    INDEX
    Explanations

    names of news organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific news organizations, publications, and agencies

    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
    riages
    -0.90
    ages
    -0.90
    liners
    -0.83
    ities
    -0.82
    rencies
    -0.81
    flows
    -0.80
    codes
    -0.80
    ships
    -0.78
     Adin
    -0.78
    pees
    -0.77
    POSITIVE LOGITS
     staffer
    1.15
     spokeswoman
    1.12
     spokesperson
    1.10
     spokesman
    1.03
     employee
    1.02
     colleague
    1.01
     representative
    0.94
     classmate
    0.91
     statement
    0.88
     broch
    0.85
    Activations Density 0.374%

    No Known Activations