© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10654
    Prev
    Next
    INDEX
    Explanations

    instances of the word "above"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "above" as a reference point or indicator within the text

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
    izens
    -0.66
    aceous
    -0.62
    ForgeModLoader
    -0.56
    eness
    -0.56
    iform
    -0.55
    xes
    -0.55
    Mail
    -0.55
    Faith
    -0.54
    ULTS
    -0.54
    POSITIVE LOGITS
    mentioned
    1.73
     mentioned
    1.14
    ground
    1.13
    above
    0.87
    lihood
    0.83
     âĨij
    0.79
     cited
    0.79
     quoted
    0.74
     alluded
    0.73
     referenced
    0.71
    Activations Density 0.026%

    No Known Activations