© 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. 7-RES-JB
    11. 23643
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning physical movement or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "around."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qua
    -0.76
    hetical
    -0.76
    ged
    -0.71
    iPhone
    -0.70
    BT
    -0.66
    iston
    -0.65
    vi
    -0.64
    jo
    -0.63
    ENS
    -0.61
    Sil
    -0.58
    POSITIVE LOGITS
     corners
    0.84
    atform
    0.83
     town
    0.80
    essage
    0.79
     freely
    0.78
    bilt
    0.75
    bag
    0.74
    bags
    0.72
    unin
    0.72
    anchester
    0.72
    Activations Density 0.035%

    No Known Activations