© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 535
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating something is below a certain threshold

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "below" followed by numerical values

    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
    MM
    -0.80
    Sense
    -0.75
    RAW
    -0.74
    Choice
    -0.72
    Frames
    -0.66
    Pros
    -0.66
    =-=-=-=-=-=-=-=-
    -0.65
    Ring
    -0.65
    Ton
    -0.65
     Sense
    -0.64
    POSITIVE LOGITS
     veter
    0.78
    querque
    0.72
     grade
    0.71
    neath
    0.71
     plateau
    0.71
    grade
    0.71
     tradem
    0.69
     trending
    0.69
    ground
    0.69
     below
    0.67
    Activations Density 0.027%

    No Known Activations