© 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. 6458
    Prev
    Next
    INDEX
    Explanations

    the word "midst" or phrases indicating a current state or situation

    oai_token-act-pair · gpt-3.5-turbo
    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
    izations
    -0.70
     visas
    -0.69
    exempt
    -0.68
    ishers
    -0.66
    ggies
    -0.65
    do
    -0.62
    isher
    -0.61
     impe
    -0.61
     guarantee
    -0.61
     subp
    -0.61
    POSITIVE LOGITS
    pace
    0.90
    cape
    0.85
    ï¸
    0.81
    entimes
    0.80
    achine
    0.79
    lehem
    0.78
    paces
    0.74
    £ı
    0.73
    )=(
    0.73
    borough
    0.72
    Activations Density 0.006%

    No Known Activations