© 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. 6-RES-JB
    11. 13606
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'marching'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "march" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terness
    -0.77
    etheless
    -0.69
    omial
    -0.66
     juicy
    -0.65
     remorse
    -0.65
    communication
    -0.64
     magnification
    -0.64
    xus
    -0.64
    levant
    -0.64
     gracious
    -0.63
    POSITIVE LOGITS
     marching
    0.95
    iage
    0.92
     marches
    0.87
     marched
    0.86
     march
    0.85
    itzer
    0.79
    igraph
    0.79
    along
    0.78
     toward
    0.77
     towards
    0.76
    Activations Density 0.020%

    No Known Activations