© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "ab" such as "abysmally" or "abduction"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "ab-" in various contexts

    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
    enegger
    -0.74
    geist
    -0.73
     Maker
    -0.71
     Fields
    -0.69
     Jobs
    -0.69
    OPLE
    -0.69
    DragonMagazine
    -0.67
     Millennium
    -0.67
     Dodd
    -0.66
     ATI
    -0.66
    POSITIVE LOGITS
    raham
    0.96
    omination
    0.89
    ibi
    0.87
    bey
    0.87
    eatures
    0.85
    rog
    0.82
    anus
    0.82
    ab
    0.82
    ¥ŀ
    0.81
    ressing
    0.80
    Activations Density 0.006%

    No Known Activations