© 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. 1-RES-JB
    11. 21765
    Prev
    Next
    INDEX
    Explanations

    phrases related to the interpretation of information or laws

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "interpret" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Du
    -0.74
    trap
    -0.71
    thin
    -0.71
    eworld
    -0.71
    ggies
    -0.64
     Rath
    -0.64
    coat
    -0.62
    hall
    -0.62
    levels
    -0.61
    tra
    -0.61
    POSITIVE LOGITS
     interpret
    1.30
     interpreted
    1.23
     interpreting
    1.22
     interpre
    1.17
     Interpret
    1.11
     interpretations
    1.06
     interpretation
    1.06
     guiActiveUn
    0.98
    interpret
    0.98
     misinterpret
    0.92
    Activations Density 0.011%

    No Known Activations