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. 23826
    Prev
    Next
    INDEX
    Explanations

    phrases related to patriotism and principles

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing collective responsibility and action

    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
    aws
    -0.65
    UC
    -0.63
    GMT
    -0.62
    arthed
    -0.62
    BAT
    -0.61
    Tes
    -0.61
    card
    -0.60
     Powered
    -0.60
    BACK
    -0.59
    ¶
    -0.59
    POSITIVE LOGITS
     thereby
    1.14
     consequently
    1.12
     thus
    1.08
     therefore
    1.05
     vice
    1.00
     hence
    0.99
     then
    0.86
     THEN
    0.85
     possibly
    0.83
     thence
    0.82
    Activations Density 0.632%

    No Known Activations