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. 23535
    Prev
    Next
    INDEX
    Explanations

    the characters 'Ļ' or 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    negations or denials

    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
     mathemat
    -0.78
     successes
    -0.69
     Seym
    -0.64
     Imag
    -0.64
     Skydragon
    -0.64
     Gutenberg
    -0.64
     Nanto
    -0.64
     Lawn
    -0.63
     Scenes
    -0.63
     Companion
    -0.63
    POSITIVE LOGITS
    ï¸ı
    0.95
    ï¸
    0.91
    sure
    0.88
    hip
    0.87
    agree
    0.85
    âĶĢ
    0.83
    yet
    0.82
    ðŁĺ
    0.81
    ski
    0.80
    le
    0.80
    Activations Density 0.213%

    No Known Activations