© 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. 1-RES-JB
    11. 20171
    Prev
    Next
    INDEX
    Explanations

    components or parts within a larger system or product

    oai_token-act-pair · gpt-3.5-turbo

    the term "component" and related references to parts or elements of a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geon
    -0.82
    chie
    -0.76
    ield
    -0.70
    geons
    -0.69
    kers
    -0.69
    sen
    -0.69
    FL
    -0.68
    standing
    -0.66
    ITED
    -0.66
    fm
    -0.66
    POSITIVE LOGITS
     components
    1.30
     Components
    1.18
     component
    1.06
     Component
    0.94
     parts
    0.92
    onents
    0.86
     diagrams
    0.83
     installer
    0.82
     ancest
    0.81
    component
    0.81
    Activations Density 0.009%

    No Known Activations