© 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. 4-RES-JB
    11. 19937
    Prev
    Next
    INDEX
    Explanations

    mentions or references to government or politics

    oai_token-act-pair · gpt-3.5-turbo

    letters or abbreviations related to government entities

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

    No Comments

    Negative Logits
    ÄŁ
    -0.64
    ks
    -0.63
    taboola
    -0.61
    cause
    -0.58
    racuse
    -0.58
    ark
    -0.57
    mx
    -0.57
    tis
    -0.57
    hex
    -0.56
    let
    -0.56
    POSITIVE LOGITS
    ULAR
    1.05
    ING
    1.05
    ION
    1.04
    ERY
    1.03
    ISH
    1.02
    ILL
    1.02
    IFIED
    1.00
    OUS
    1.00
    ENCY
    1.00
    EMENT
    1.00
    Activations Density 0.105%

    No Known Activations