© 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. 24279
    Prev
    Next
    INDEX
    Explanations

    terms related to the name "Rus" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those related to political figures

    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
     magnitude
    -0.70
     lesson
    -0.63
     testament
    -0.62
    ITNESS
    -0.60
    ĺħ
    -0.59
     sovere
    -0.59
     fet
    -0.59
    requisites
    -0.58
     stakes
    -0.57
    ahon
    -0.57
    POSITIVE LOGITS
    hes
    0.97
    sell
    0.91
    iosity
    0.89
    atile
    0.87
    ultan
    0.85
    ç·
    0.84
    hea
    0.83
    velt
    0.83
    auld
    0.83
    é¾įåĸļ士
    0.83
    Activations Density 0.011%

    No Known Activations