Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17724
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ples"

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of "multiples" in contexts relating to shared characteristics or groupings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vald
    -0.65
     slack
    -0.61
     atmosphere
    -0.61
     ventilation
    -0.61
     ozone
    -0.60
     Insect
    -0.60
     interstate
    -0.60
     Esk
    -0.59
     fault
    -0.58
     advisory
    -0.57
    POSITIVE LOGITS
    ples
    4.86
    pled
    2.58
    pling
    2.46
    ple
    2.12
    pler
    1.73
    plings
    1.68
    bles
    1.36
    plates
    1.35
    plets
    1.23
    ply
    1.19
    Activations Density 0.010%

    No Known Activations