© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1909
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific situations or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when."

    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
    agin
    -0.80
    thal
    -0.66
    Bas
    -0.63
    ictive
    -0.63
    yan
    -0.63
    Es
    -0.62
    ha
    -0.62
    aches
    -0.62
    gan
    -0.61
    bas
    -0.61
    POSITIVE LOGITS
    soever
    1.23
     asked
    0.82
     confronted
    0.81
    irlf
    0.79
     pressed
    0.78
     they
    0.76
     contacted
    0.72
    */(
    0.71
     she
    0.71
     faced
    0.70
    Activations Density 0.124%

    No Known Activations