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

    specific items or objects from various contexts and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific items or concepts associated with the phrase "from."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rils
    -0.82
    opausal
    -0.81
    mun
    -0.81
    ratulations
    -0.80
    pes
    -0.76
    merce
    -0.74
    enaries
    -0.72
    othe
    -0.72
    perty
    -0.71
    threat
    -0.70
    POSITIVE LOGITS
     afar
    1.27
     whence
    1.04
     antiquity
    0.90
     scrimmage
    0.84
     scratch
    0.82
     nowhere
    0.79
     Epic
    0.77
     Anaheim
    0.77
     Shutterstock
    0.75
     childhood
    0.73
    Activations Density 0.134%

    No Known Activations