© 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. 0-RES-JB
    11. 9552
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to a diverse or wide variety of items

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of collections and the concept of absurdity

    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
     lot
    -0.89
    ggies
    -0.83
    versions
    -0.78
     certain
    -0.76
    venge
    -0.74
    YES
    -0.73
     bunch
    -0.72
     LOT
    -0.71
    ctors
    -0.70
    ware
    -0.69
    POSITIVE LOGITS
     enigmatic
    1.26
     exotic
    1.20
     obscure
    1.17
     absurd
    1.16
     elegant
    1.12
     intriguing
    1.12
     esoteric
    1.09
     arcane
    1.08
     astonishing
    1.07
     eccentric
    1.07
    Activations Density 0.112%

    No Known Activations