© 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. 6-RES-JB
    11. 14503
    Prev
    Next
    INDEX
    Explanations

    numerical data related to rates and prices

    oai_token-act-pair · gpt-3.5-turbo

    collocations related to high rates and prices in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iverse
    -0.73
    SPONSORED
    -0.71
    Wing
    -0.68
     Gleaming
    -0.67
     guiActiveUn
    -0.66
    thin
    -0.64
    tiny
    -0.63
    GV
    -0.62
    ADRA
    -0.62
    Pub
    -0.62
    POSITIVE LOGITS
     (>
    0.94
     (<
    0.71
     levels
    0.67
    atoes
    0.66
     dur
    0.65
     relative
    0.63
    \">
    0.63
     rates
    0.63
     earners
    0.62
    ovi
    0.61
    Activations Density 0.200%

    No Known Activations