© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 12702
    Prev
    Next
    INDEX
    Explanations

    words related to destruction or damage

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "wreck" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anamo
    -0.77
    DragonMagazine
    -0.71
    western
    -0.67
     UID
    -0.63
    rison
    -0.63
     Kubrick
    -0.63
     Alps
    -0.63
    Hop
    -0.62
    animous
    -0.61
     Quartz
    -0.61
    POSITIVE LOGITS
     havoc
    1.27
     wre
    1.26
    cks
    1.03
    \\\\
    0.96
     wreck
    0.75
     Ley
    0.74
     Shoals
    0.73
    fare
    0.72
    *=-
    0.71
    ©¶æ¥µ
    0.69
    Activations Density 0.011%

    No Known Activations