© 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. 11-RES-JB
    11. 20798
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific research and the scientists involved in it

    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
    acia
    -0.78
    soType
    -0.77
    VERTISEMENT
    -0.74
    Dialogue
    -0.71
    assi
    -0.71
     Synd
    -0.67
     Salary
    -0.65
     Glory
    -0.64
    Govern
    -0.62
    Choice
    -0.62
    POSITIVE LOGITS
     hypothes
    1.56
     theor
    1.36
     hypothesized
    1.22
     conject
    1.19
     speculate
    1.15
     detected
    1.13
     discovered
    1.12
     astronomers
    1.11
     detect
    1.09
     conjecture
    1.09
    Activations Density 0.239%

    No Known Activations