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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 18794
    Prev
    Next
    INDEX
    Explanations

    locations or venues indicated by the word "center"

    oai_token-act-pair · gpt-3.5-turbo

    references to various centers, likely venues or locations for events

    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
    wcsstore
    -0.77
    soDeliveryDate
    -0.68
    ests
    -0.65
     proof
    -0.62
    ::::::::
    -0.62
    è¦ļéĨĴ
    -0.61
    ppings
    -0.60
     intox
    -0.60
    ths
    -0.60
     sentient
    -0.59
    POSITIVE LOGITS
    pieces
    0.96
     Plaza
    0.90
    eous
    0.83
    Aren
    0.77
    Point
    0.75
    itect
    0.75
     Center
    0.74
    onne
    0.72
     Towers
    0.72
    field
    0.71
    Activations Density 0.022%

    No Known Activations