© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5000
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks or activities

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "the" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    buster
    -0.68
    icho
    -0.62
    emen
    -0.57
    illon
    -0.55
    amera
    -0.55
    nesty
    -0.55
    mont
    -0.55
    inently
    -0.55
    anova
    -0.55
     suggests
    -0.54
    POSITIVE LOGITS
     slightest
    1.28
     same
    1.12
     smallest
    0.99
     rest
    0.96
     entirety
    0.95
    ses
    0.94
     remainder
    0.94
     whole
    0.93
     entire
    0.92
     proverbial
    0.91
    Activations Density 1.028%

    No Known Activations