Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23672
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements, as well as alphanumeric codes and identifiers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and references to programming elements or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.92
    Þ
    -0.89
    ß
    -0.80
     pione
    -0.78
     tremend
    -0.78
     exting
    -0.77
     occas
    -0.77
    ò
    -0.76
    aditional
    -0.76
     oun
    -0.76
    POSITIVE LOGITS
    eret
    0.48
    Merit
    0.48
    wcsstore
    0.47
    athan
    0.45
    't
    0.44
    bryce
    0.43
    gex
    0.43
    Course
    0.43
    thereum
    0.43
    forge
    0.43
    Activations Density 0.938%

    No Known Activations