© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7303
    Prev
    Next
    INDEX
    Explanations

    technical terms related to digital tools and functionalities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific tools and features related to technology or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outwe
    -0.73
    daq
    -0.73
    "},"
    -0.68
    .}
    -0.68
    etheless
    -0.68
     margins
    -0.68
    ilipp
    -0.65
    aretz
    -0.65
     anyway
    -0.64
    reon
    -0.62
    POSITIVE LOGITS
     Allows
    1.46
     Provides
    1.37
    Allows
    1.28
     Contains
    1.25
     Located
    1.17
     Used
    1.13
     Designed
    1.13
     Adds
    1.12
     Provide
    1.09
     Similar
    1.08
    Activations Density 0.173%

    No Known Activations