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. 16431
    Prev
    Next
    INDEX
    Explanations

    the word "of" followed by a numeric value or a pronoun

    oai_token-act-pair · gpt-3.5-turbo

    references to fractions or percentages, particularly focusing on "half" and its related 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
    arella
    -0.70
    AMI
    -0.65
     exagger
    -0.63
    affer
    -0.62
    acus
    -0.61
    abilia
    -0.60
     grouping
    -0.60
     blur
    -0.60
     palp
    -0.59
    hof
    -0.58
    POSITIVE LOGITS
     Sevent
    0.77
     respondents
    0.73
    ths
    0.69
    pees
    0.62
     dozen
    0.62
    nir
    0.61
     Americans
    0.60
     households
    0.59
     America
    0.59
    OUR
    0.59
    Activations Density 0.063%

    No Known Activations