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. 17477
    Prev
    Next
    INDEX
    Explanations

    phrases related to applying pressure or causing influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of pressure, particularly in a societal or systemic context

    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
    SourceFile
    -0.76
    mpeg
    -0.74
     Klux
    -0.70
    acements
    -0.69
    aces
    -0.69
    ults
    -0.67
    imilar
    -0.67
    ISA
    -0.66
    olf
    -0.65
    lene
    -0.63
    POSITIVE LOGITS
    erous
    1.21
     behalf
    1.00
     shoulders
    0.84
    shore
    0.83
    coming
    0.79
    rez
    0.73
    ibaba
    0.72
     tyres
    0.69
     brakes
    0.69
     top
    0.68
    Activations Density 0.068%

    No Known Activations