© 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. 2-RES-JB
    11. 12670
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mach" with different numeric values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Machado" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0000000000000000
    -0.71
    SHIP
    -0.69
     Citizens
    -0.69
     Vive
    -0.67
     Physicians
    -0.65
    payer
    -0.64
     Sony
    -0.63
    etheless
    -0.62
    Rush
    -0.62
     Electronic
    -0.62
    POSITIVE LOGITS
    inery
    1.12
    Mach
    0.94
     Mach
    0.93
    ineries
    0.80
    inations
    0.77
    insk
    0.76
    romy
    0.75
     corrid
    0.74
     mathemat
    0.73
    itud
    0.72
    Activations Density 0.008%

    No Known Activations