© 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. 3-RES-JB
    11. 15238
    Prev
    Next
    INDEX
    Explanations

    ways or methods to accomplish tasks or solve problems

    oai_token-act-pair · gpt-3.5-turbo

    references to methods or approaches to achieve goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFIED
    -0.73
    ı
    -0.65
    uster
    -0.64
    inally
    -0.62
    ãĥ¡
    -0.62
    usters
    -0.61
     1903
    -0.60
    isher
    -0.58
    iversity
    -0.58
    inately
    -0.58
    POSITIVE LOGITS
    finding
    0.94
     ways
    0.87
     Ways
    0.87
    cale
    0.86
    styles
    0.79
    hell
    0.79
    pointers
    0.79
    terday
    0.76
    soDeliveryDate
    0.76
    hift
    0.75
    Activations Density 0.021%

    No Known Activations