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. 16607
    Prev
    Next
    INDEX
    Explanations

    phrases with the expression "just in time."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "time" along with its variations and contexts

    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
    LCS
    -0.78
    ramid
    -0.76
    avored
    -0.65
    igent
    -0.64
    avorite
    -0.64
    otally
    -0.64
    iants
    -0.64
    ached
    -0.63
    doms
    -0.63
    alach
    -0.61
    POSITIVE LOGITS
    trial
    0.82
    frames
    0.72
    ãĥ¼ãĥĨ
    0.69
    frame
    0.67
    bral
    0.67
    blank
    0.66
    rx
    0.66
    Shape
    0.65
    çĦ
    0.65
    î
    0.64
    Activations Density 0.024%

    No Known Activations