© 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. 2-RES-JB
    11. 22152
    Prev
    Next
    INDEX
    Explanations

    words related to tense situations or environments

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to levels of tension or stress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cart
    -0.87
    adr
    -0.85
    alach
    -0.81
    olicited
    -0.78
    ombie
    -0.77
    haps
    -0.74
    apple
    -0.74
    sites
    -0.74
    opsy
    -0.74
    issors
    -0.74
    POSITIVE LOGITS
     tense
    1.19
     tension
    0.95
     standoff
    0.87
     situations
    0.81
     mood
    0.80
    ness
    0.79
     Situation
    0.79
    terday
    0.78
     condition
    0.76
     situation
    0.75
    Activations Density 0.017%

    No Known Activations