© 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. 2-RES-JB
    11. 23638
    Prev
    Next
    INDEX
    Explanations

    words related to regional locations or abbreviations, specifically focusing on the letters 'VA'

    oai_token-act-pair · gpt-3.5-turbo

    references to the acronym "VA" and its related significance in various contexts

    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
    wcsstore
    -0.82
    cold
    -0.77
    court
    -0.72
    bread
    -0.72
    pins
    -0.72
    handler
    -0.72
    cook
    -0.71
    lins
    -0.70
    */(
    -0.67
     conflic
    -0.67
    POSITIVE LOGITS
    VA
    1.17
    ULT
    1.01
    BIL
    0.99
    III
    0.92
    HS
    0.91
    UAL
    0.90
    qua
    0.89
    Va
    0.87
    ULTS
    0.87
    akeru
    0.86
    Activations Density 0.008%

    No Known Activations