© 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. 10-RES-JB
    11. 8365
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficult or challenging situations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iphate
    -0.81
    ¬¼
    -0.77
    ommel
    -0.70
    ãĤ¨ãĥ«
    -0.70
    ernaut
    -0.69
    edom
    -0.69
    sburg
    -0.69
    »Ĵ
    -0.67
    pheus
    -0.67
    itational
    -0.67
    POSITIVE LOGITS
     resulting
    1.09
     preferring
    1.08
     forcing
    1.07
     exacerbated
    1.07
     owing
    1.06
     wasting
    1.04
     depri
    1.04
     unable
    1.03
     hampered
    1.01
     causing
    1.01
    Activations Density 0.339%

    No Known Activations