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. 2-RES-JB
    6. 16874
    Prev
    Next
    INDEX
    Explanations

    adverbs denoting equality or similarity

    oai_token-act-pair · gpt-3.5-turbo

    the term "equally" and related phrases that emphasize balance or parity in comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LD
    -0.82
     Vaj
    -0.79
     Dwell
    -0.72
    ocene
    -0.70
     Archives
    -0.70
    URE
    -0.69
     Origins
    -0.68
    liest
    -0.67
    ASE
    -0.65
     Canaver
    -0.65
    POSITIVE LOGITS
     equally
    0.90
     minded
    0.87
    itably
    0.81
     spaced
    0.81
    etrical
    0.77
     situated
    0.77
    inguishable
    0.76
     sized
    0.76
    imilar
    0.75
    sheets
    0.75
    Activations Density 0.006%

    No Known Activations