© 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. 10-RES-JB
    11. 12835
    Prev
    Next
    INDEX
    Explanations

    words related to the process of creation or development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the development or creation of projects, standards, or concepts

    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
    ĪĴ
    -0.63
    MORE
    -0.63
    Zone
    -0.59
    edge
    -0.58
    Points
    -0.55
    VERTISEMENT
    -0.55
    marg
    -0.54
    rium
    -0.54
    ãģĦ
    -0.52
    Sing
    -0.52
    POSITIVE LOGITS
     by
    1.11
     jointly
    1.00
     unanimously
    0.95
     pursuant
    0.91
     during
    0.88
     earlier
    0.87
     shortly
    0.83
     originally
    0.83
     collabor
    0.82
     expressly
    0.82
    Activations Density 0.224%

    No Known Activations