© 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. 3-RES-JB
    11. 14731
    Prev
    Next
    INDEX
    Explanations

    technical details and product features, especially related to pricing, specifications, and launches

    oai_token-act-pair · gpt-3.5-turbo

    references to product specifications and pricing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nat
    -0.88
     Soros
    -0.83
    racial
    -0.81
    quest
    -0.76
    polit
    -0.76
    Els
    -0.73
     Transcript
    -0.73
    nder
    -0.70
     Homeless
    -0.69
     Lump
    -0.68
    POSITIVE LOGITS
     specifications
    1.11
     manufacturers
    1.11
     specs
    1.10
     warranties
    1.09
     OEM
    1.09
     manufactures
    1.09
     manufacturer
    1.03
     brands
    0.97
     chipset
    0.95
    amsung
    0.94
    Activations Density 0.663%

    No Known Activations