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. 12429
    Prev
    Next
    INDEX
    Explanations

    direct speech marked with quotations

    oai_token-act-pair · gpt-3.5-turbo

    dialogue punctuation, particularly the use of quotation marks

    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
    avorite
    -0.89
    irtual
    -0.71
    ¥ŀ
    -0.69
     vide
    -0.68
     Lauder
    -0.67
     deterrent
    -0.65
     satell
    -0.65
    phthal
    -0.64
     triv
    -0.64
     subsid
    -0.62
    POSITIVE LOGITS
    Oh
    1.01
    Hey
    0.99
    hey
    0.94
    Sir
    0.88
    Yo
    0.85
    I
    0.84
    cause
    0.83
    Everybody
    0.83
    Wait
    0.81
    Let
    0.80
    Activations Density 0.087%

    No Known Activations