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. 2135
    Prev
    Next
    INDEX
    Explanations

    mentions of President Trump and his actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    possessive constructions referencing Donald Trump

    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
    lehem
    -0.87
    hari
    -0.86
    ":[
    -0.76
     Rowling
    -0.75
    anges
    -0.75
    lin
    -0.73
    lling
    -0.68
     Logged
    -0.68
    liga
    -0.68
     Kubrick
    -0.67
    POSITIVE LOGITS
     own
    1.30
     newest
    1.05
     penchant
    1.00
     signature
    0.97
     insistence
    0.97
     plight
    0.96
     inability
    0.95
     efforts
    0.95
     antics
    0.94
     newfound
    0.94
    Activations Density 0.161%

    No Known Activations