© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 7951
    Prev
    Next
    INDEX
    Explanations

    words ending with the suffix '-ies'

    oai_token-act-pair · gpt-3.5-turbo

    plural noun forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èª
    -0.71
    channelAvailability
    -0.70
    adium
    -0.70
    asio
    -0.69
    handle
    -0.68
    thia
    -0.67
    ŃĶ
    -0.62
     Inquis
    -0.60
    Oracle
    -0.60
     srfAttach
    -0.59
    POSITIVE LOGITS
    ystem
    1.03
    poons
    0.92
    pace
    0.87
    hips
    0.83
    omething
    0.83
    ies
    0.82
    eries
    0.82
    hops
    0.81
    uits
    0.80
    chool
    0.78
    Activations Density 0.029%

    No Known Activations