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. 0-RES-JB
    6. 10775
    Prev
    Next
    INDEX
    Explanations

    the last name "Sullivan" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "ull."

    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
    making
    -0.71
     development
    -0.68
     improv
    -0.64
     Coleman
    -0.64
     coding
    -0.62
     date
    -0.60
     voic
    -0.59
     house
    -0.59
     hackers
    -0.59
     condom
    -0.59
    POSITIVE LOGITS
    ull
    4.59
    ULL
    1.92
    ulla
    1.84
    ully
    1.23
    ul
    1.22
    ulk
    1.21
    ullah
    1.19
    utt
    1.18
    ueller
    1.13
    illi
    1.13
    Activations Density 0.016%

    No Known Activations