© 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. 22010
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to military or conflict

    oai_token-act-pair · gpt-3.5-turbo

    words related to military and victory

    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
    «ĺ
    -0.75
    Ĥª
    -0.75
    umbnails
    -0.73
    ãģ®å®
    -0.67
    OSS
    -0.67
    issance
    -0.65
     cleaners
    -0.65
    ERG
    -0.63
    rehensive
    -0.63
    sych
    -0.62
    POSITIVE LOGITS
    nesday
    0.88
     Alive
    0.80
    vier
    0.77
    nes
    0.76
    hof
    0.76
    heimer
    0.74
     Created
    0.73
    sell
    0.72
    zan
    0.72
    nant
    0.72
    Activations Density 0.032%

    No Known Activations