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. 1752
    Prev
    Next
    INDEX
    Explanations

    words with special characters that are not typically found in English

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols in the text

    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
    ITNESS
    -0.76
     Coliseum
    -0.76
     Commodore
    -0.75
    iflower
    -0.73
     Leilan
    -0.72
    WARD
    -0.72
     DMV
    -0.67
    wards
    -0.65
     combustion
    -0.63
    bury
    -0.60
    POSITIVE LOGITS
    ı
    1.26
    ¼
    1.25
    ½
    1.21
    ¾
    1.19
    ł
    1.18
    ĭ
    1.18
    Ĵ
    1.16
    ĵ
    1.16
    ¸
    1.14
    Į
    1.10
    Activations Density 0.012%

    No Known Activations