© 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. 1-RES-JB
    11. 22639
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to devices and mechanisms, as well as names or references to a particular individual "Shimano"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly related to people named Shimano

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctuary
    -0.79
     Leap
    -0.74
     Carbuncle
    -0.73
    DragonMagazine
    -0.72
     livestream
    -0.71
    éĹ
    -0.69
    ocument
    -0.69
    cript
    -0.68
    tumblr
    -0.65
    AFTA
    -0.64
    POSITIVE LOGITS
     molded
    0.94
     adapters
    0.93
     manufact
    0.89
     Specifications
    0.87
    rylic
    0.86
     specifications
    0.86
     adapter
    0.84
     accessories
    0.84
     blades
    0.84
     toler
    0.84
    Activations Density 0.518%

    No Known Activations