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. 11-RES-JB
    6. 19557
    Prev
    Next
    INDEX
    Explanations

    words that contain the substring "om"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "om" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UB
    -0.65
    VICE
    -0.64
    LIST
    -0.61
     convict
    -0.59
     nexus
    -0.59
     caric
    -0.58
    draw
    -0.58
    Wr
    -0.57
     skim
    -0.57
     overpower
    -0.56
    POSITIVE LOGITS
    puter
    1.30
    merce
    1.17
    pson
    1.16
    otive
    1.14
    obile
    1.14
    orrow
    1.12
    icro
    1.11
    mercial
    1.11
    plete
    1.10
    agnetic
    1.08
    Activations Density 0.047%

    No Known Activations