© 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. 8-RES-JB
    11. 7612
    Prev
    Next
    INDEX
    Explanations

    references to the primary topic or main theme in a given context

    oai_token-act-pair · gpt-3.5-turbo

    references to a central theme or main topic in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ania
    -0.81
    asca
    -0.78
    idden
    -0.71
    OUGH
    -0.68
    named
    -0.68
    ston
    -0.66
    apons
    -0.64
    ibrary
    -0.63
    mia
    -0.62
    ccess
    -0.61
    POSITIVE LOGITS
    starter
    0.87
    rite
    0.84
     squarely
    0.80
    fulness
    0.78
    Goal
    0.76
     focus
    0.76
     focuses
    0.76
    ivation
    0.75
     focused
    0.75
    tenance
    0.72
    Activations Density 0.034%

    No Known Activations