© 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. 8-RES-JB
    11. 24034
    Prev
    Next
    INDEX
    Explanations

    phrases related to building or creating something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of building or creating something new

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Contents
    -0.70
    aunts
    -0.68
    errors
    -0.68
    flies
    -0.68
    tm
    -0.66
    mates
    -0.66
    igators
    -0.66
    ESPN
    -0.65
     aliases
    -0.64
    notes
    -0.64
    POSITIVE LOGITS
     comprehensive
    1.10
     cohesive
    1.07
     unified
    1.07
     viable
    1.03
     meaningful
    1.02
     fuller
    1.01
    rouse
    1.01
     coherent
    1.00
     realistic
    0.96
     definitive
    0.96
    Activations Density 0.469%

    No Known Activations