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. 3-RES-JB
    6. 14622
    Prev
    Next
    INDEX
    Explanations

    abbreviations ending with 'As'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of acronyms and specific biological terms related to RNA

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cir
    -0.75
     Temper
    -0.68
    yss
    -0.66
     Mile
    -0.64
    hold
    -0.63
     Hath
    -0.63
    ¥µ
    -0.62
    ãĤ©
    -0.62
    ãĥ´ãĤ¡
    -0.62
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.60
    POSITIVE LOGITS
    ources
    0.99
    ourcing
    0.91
    etting
    0.87
    hee
    0.85
    Ds
    0.84
    akeru
    0.83
    atives
    0.80
    ourced
    0.79
    ucks
    0.76
    amsung
    0.75
    Activations Density 0.104%

    No Known Activations