Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 941
    Prev
    Next
    INDEX
    Explanations

    proper names of public figures such as politicians and authors

    oai_token-act-pair · gpt-3.5-turbo

    prominent political figures and their statements or actions

    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
    asketball
    -0.59
    venge
    -0.55
    Split
    -0.53
    ascar
    -0.52
    agonist
    -0.52
    achelor
    -0.49
    amily
    -0.49
    emetery
    -0.49
    oppable
    -0.49
    emale
    -0.49
    POSITIVE LOGITS
     recommends
    0.69
     et
    0.58
     ®
    0.57
     patent
    0.56
     gmaxwell
    0.56
     proposes
    0.55
    / 
    0.55
     emphasizes
    0.55
     warns
    0.54
    SourceFile
    0.51
    Activations Density 1.886%

    No Known Activations