© 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. 0-RES-JB
    11. 23118
    Prev
    Next
    INDEX
    Explanations

    specific keywords such as "typed", "coded", "stamped", "formatted", and "packaged"

    oai_token-act-pair · gpt-3.5-turbo

    words related to digital actions and processes, particularly those involving data manipulation or security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osi
    -0.86
    root
    -0.85
    efficiency
    -0.72
    benefit
    -0.71
    itiveness
    -0.70
    berra
    -0.67
    oe
    -0.67
    ysis
    -0.67
     erection
    -0.67
    anse
    -0.66
    POSITIVE LOGITS
     typed
    1.96
     coded
    1.94
     formatted
    1.76
     emailed
    1.74
     translated
    1.68
     edited
    1.68
     printed
    1.57
     mapped
    1.56
     tagged
    1.53
     mailed
    1.52
    Activations Density 0.059%

    No Known Activations