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. 18682
    Prev
    Next
    INDEX
    Explanations

    requests for actions relating to engagement, interaction, or support, such as leaving comments, making donations, and sharing content

    oai_token-act-pair · gpt-3.5-turbo

    requests related to user interaction and engagement

    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
    Marginal
    -0.58
    roots
    -0.55
     amput
    -0.54
     destabil
    -0.53
    ³³³³³³³³
    -0.53
    rational
    -0.53
    define
    -0.51
     Historically
    -0.50
    cffffcc
    -0.50
    gain
    -0.50
    POSITIVE LOGITS
     :)
    0.94
     ;)
    0.92
     bookmark
    0.84
     ðŁĻĤ
    0.78
    ebin
    0.77
     THANK
    0.71
     coupon
    0.70
     subscription
    0.70
     Patreon
    0.70
     www
    0.69
    Activations Density 1.598%

    No Known Activations