© 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. 9-RES-JB
    11. 14863
    Prev
    Next
    INDEX
    Explanations

    words related to war and conflict

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "arrest."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.86
    ¬¼
    -0.82
    e
    -0.69
    assetsadobe
    -0.67
    ĨĴ
    -0.66
    eries
    -0.65
    er
    -0.64
    insula
    -0.63
    éĹĺ
    -0.63
    ĪĴ
    -0.62
    POSITIVE LOGITS
    riors
    1.06
    beit
    1.04
    thur
    1.04
    ctica
    1.03
    riage
    1.01
    acter
    1.00
    acters
    0.99
    ithmetic
    0.98
    ashtra
    0.94
    allel
    0.92
    Activations Density 0.053%

    No Known Activations