© 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. 1-RES-JB
    11. 24304
    Prev
    Next
    INDEX
    Explanations

    words related to marking or emphasizing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mark" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     substantially
    -0.71
     mishand
    -0.69
     moderately
    -0.69
     surviv
    -0.68
     agon
    -0.67
     VIDE
    -0.67
     decomp
    -0.67
     positively
    -0.66
     mono
    -0.66
    ADS
    -0.65
    POSITIVE LOGITS
    marks
    1.59
    mark
    1.57
    emark
    1.15
    furt
    1.08
    manship
    1.08
    ertodd
    1.00
    eters
    0.97
    marked
    0.93
    uments
    0.90
    hof
    0.87
    Activations Density 0.008%

    No Known Activations