© 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. 4-RES-JB
    6. 11077
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Pravda"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Rav" in the context of political discussions

    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
    lder
    -0.82
    print
    -0.72
    erity
    -0.71
    soDeliveryDate
    -0.70
    CRE
    -0.68
    bright
    -0.67
    ça
    -0.66
    hyde
    -0.66
    houses
    -0.66
    grass
    -0.64
    POSITIVE LOGITS
    itational
    1.17
    igor
    0.99
    itz
    0.90
    atar
    0.88
    ski
    0.86
    idation
    0.86
    iol
    0.86
    eus
    0.86
    ision
    0.86
    iev
    0.85
    Activations Density 0.009%

    No Known Activations