© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 18684
    Prev
    Next
    INDEX
    Explanations

    lists or collections of various items or entities

    oai_token-act-pair · gpt-3.5-turbo

    discussions about extensive lists or itemization

    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
     interference
    -0.73
     Samar
    -0.72
     ignition
    -0.71
     Galile
    -0.70
     brakes
    -0.67
    Ther
    -0.66
     interrupt
    -0.65
     grounding
    -0.65
     brake
    -0.65
     cents
    -0.64
    POSITIVE LOGITS
     curated
    1.14
     compiled
    1.10
     lists
    1.09
     list
    1.04
     Lists
    1.04
     alphabet
    1.04
     comprised
    1.01
     littered
    1.01
     sorted
    0.99
     exhaustive
    0.92
    Activations Density 0.541%

    No Known Activations