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. 11638
    Prev
    Next
    INDEX
    Explanations

    information related to products and services

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate existence or state

    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
    uld
    -0.76
    aths
    -0.67
    sheet
    -0.65
    wings
    -0.65
    ickers
    -0.64
    DF
    -0.63
    sheets
    -0.62
    icum
    -0.62
    ue
    -0.61
    upt
    -0.59
    POSITIVE LOGITS
     awfully
    0.83
     tremendously
    0.79
     hardly
    0.76
     undoubtedly
    0.76
     greatly
    0.75
     sorely
    0.74
     immensely
    0.73
     gladly
    0.73
     surely
    0.72
     exceedingly
    0.72
    Activations Density 0.338%

    No Known Activations