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. 16074
    Prev
    Next
    INDEX
    Explanations

    words related to remastering

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "remaster" 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
    glers
    -0.85
    à¼
    -0.74
    gerald
    -0.72
    ãĤ¡
    -0.71
    pants
    -0.71
     Deity
    -0.68
    BOOK
    -0.68
     Petersen
    -0.67
    OPLE
    -0.66
    GY
    -0.66
    POSITIVE LOGITS
    ittance
    1.26
    ilit
    1.17
    ixed
    1.10
    uner
    1.07
    ploy
    1.05
    itt
    1.01
    ission
    1.01
    utations
    0.98
    issions
    0.97
    ovable
    0.97
    Activations Density 0.009%

    No Known Activations