© 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. 15089
    Prev
    Next
    INDEX
    Explanations

    phrases introducing additional information or continuing a thought

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases commonly used in discussions

    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
    âĦ¢:
    -0.67
     ®
    -0.64
    HOU
    -0.62
     clut
    -0.57
     !
    -0.57
     clo
    -0.56
     adorable
    -0.56
    powerful
    -0.56
     incre
    -0.55
     anew
    -0.55
    POSITIVE LOGITS
    entimes
    0.97
     secondly
    0.86
    }"
    0.84
     yeah
    0.82
     luckily
    0.81
    ertodd
    0.80
     I
    0.79
    [/
    0.78
     âĢ¦"
    0.76
     [
    0.75
    Activations Density 0.254%

    No Known Activations