© 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. 0-RES-JB
    11. 16336
    Prev
    Next
    INDEX
    Explanations

    words related to labeling or categorizing, such as "tags" or "magazines"

    oai_token-act-pair · gpt-3.5-turbo

    specific names or titles related to characters, especially those in popular culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ds
    -0.70
    orted
    -0.67
     Divide
    -0.66
    uria
    -0.65
     resistance
    -0.63
     lengths
    -0.62
    illary
    -0.61
     CES
    -0.61
     Conditions
    -0.60
    Express
    -0.59
    POSITIVE LOGITS
    Knight
    2.26
     bookmark
    1.84
    aunders
    0.98
     Tags
    0.92
     refere
    0.86
    Magazine
    0.71
    eny
    0.64
    anan
    0.63
    CLAIM
    0.62
    obook
    0.62
    Activations Density 0.012%

    No Known Activations