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. 8-RES-JB
    6. 21126
    Prev
    Next
    INDEX
    Explanations

    the word "all" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.75
    illac
    -0.75
     Kamp
    -0.70
    assembly
    -0.62
    lav
    -0.60
    ritic
    -0.59
    isition
    -0.56
    etter
    -0.56
    estamp
    -0.56
    aminer
    -0.56
    POSITIVE LOGITS
     kinds
    1.15
     sorts
    1.10
    ocating
    1.03
    usions
    1.01
    iances
    0.96
    igators
    0.91
    things
    0.88
    usion
    0.85
    udes
    0.85
    iance
    0.85
    Activations Density 0.108%

    No Known Activations