© 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. 11-RES-JB
    11. 14909
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating something has reached a peak or is at an all-time high

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increasing levels of something over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ename
    -0.72
     Cosponsors
    -0.66
    anchester
    -0.64
    heimer
    -0.62
     resemb
    -0.61
    ificantly
    -0.60
     Parables
    -0.60
     reconc
    -0.59
    rera
    -0.59
    ochet
    -0.58
    POSITIVE LOGITS
     before
    1.32
    before
    1.15
     BEFORE
    1.07
     dreamed
    0.88
     Before
    0.83
     imagined
    0.81
     imaginable
    0.79
     anticipated
    0.78
     ago
    0.78
     thanks
    0.77
    Activations Density 0.039%

    No Known Activations