© 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. 17581
    Prev
    Next
    INDEX
    Explanations

    numerical values presented in a specific format within text

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or figures in the text

    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
     padd
    -0.76
     elevation
    -0.71
     travers
    -0.70
     swallowing
    -0.68
     pastoral
    -0.68
     guarding
    -0.66
     brid
    -0.66
     railing
    -0.65
     expelled
    -0.64
     subord
    -0.64
    POSITIVE LOGITS
     SHARES
    0.97
     NCT
    0.80
    nd
    0.80
    ½
    0.79
    121
    0.79
    646
    0.79
    226
    0.78
    :{
    0.78
    rd
    0.77
    maxwell
    0.77
    Activations Density 0.079%

    No Known Activations