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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5674
    Prev
    Next
    INDEX
    Explanations

    words related to combining or merging things together

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "combine" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    den
    -0.76
    etheless
    -0.74
    fare
    -0.74
    estate
    -0.71
    bis
    -0.70
    boy
    -0.70
    writers
    -0.69
    noon
    -0.67
    shire
    -0.66
    kar
    -0.66
    POSITIVE LOGITS
    ãĤ¤ãĥĪ
    0.84
     seamlessly
    0.83
     dots
    0.82
    ively
    0.76
     sexes
    0.76
    ibilities
    0.74
     genders
    0.73
     together
    0.73
     combines
    0.71
     genres
    0.71
    Activations Density 0.033%

    No Known Activations