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. 15526
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a state of impending change or action

    oai_token-act-pair · gpt-3.5-turbo

    contexts related to being on the brink of a significant change or event

    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
    auts
    -0.66
    anche
    -0.65
    ryu
    -0.63
    umbo
    -0.63
    elo
    -0.59
    channelAvailability
    -0.58
    true
    -0.58
    anned
    -0.57
    checks
    -0.57
    argo
    -0.57
    POSITIVE LOGITS
    CONCLUS
    0.74
    Frameworks
    0.72
    usp
    0.68
    Reloaded
    0.68
    aphael
    0.66
    UTH
    0.65
    axis
    0.65
    achu
    0.65
     precip
    0.65
     heels
    0.64
    Activations Density 0.065%

    No Known Activations