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. 5226
    Prev
    Next
    INDEX
    Explanations

    information related to political parties and statistics

    oai_token-act-pair · gpt-3.5-turbo

    expressions of trust or mistrust in political 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
     oath
    -0.71
     dressing
    -0.69
    sic
    -0.67
     boiler
    -0.67
     condone
    -0.65
    mens
    -0.65
     heed
    -0.65
    sg
    -0.64
     pier
    -0.64
     vend
    -0.64
    POSITIVE LOGITS
    verages
    1.20
    Average
    1.08
     averages
    1.04
     averaged
    1.02
    Percent
    0.96
     Average
    0.95
     Percentage
    0.93
     averaging
    0.92
    glomer
    0.90
     Adjusted
    0.89
    Activations Density 0.903%

    No Known Activations