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. 3815
    Prev
    Next
    INDEX
    Explanations

    references to different types of brushes used for various activities such as painting, makeup, and grooming

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of brushes

    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
    reme
    -0.78
    oppable
    -0.72
    Sax
    -0.69
    alg
    -0.67
     Defenders
    -0.67
    rophe
    -0.67
    eon
    -0.65
    igmat
    -0.64
    ZI
    -0.63
     Founding
    -0.63
    POSITIVE LOGITS
    brush
    1.08
     brush
    0.93
     Brush
    0.92
    stroke
    0.84
     brushes
    0.84
    tip
    0.83
     strokes
    0.82
    asso
    0.82
     brist
    0.79
    ãĤĮ
    0.78
    Activations Density 0.020%

    No Known Activations