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. 11699
    Prev
    Next
    INDEX
    Explanations

    time-related expressions, particularly those indicating years and time passed

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the passage of time

    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
    ãĥ¤
    -0.76
    SourceFile
    -0.76
    Redd
    -0.73
    anooga
    -0.72
    Talk
    -0.66
    Bey
    -0.65
    edo
    -0.65
    topic
    -0.64
    icum
    -0.64
    Cho
    -0.63
    POSITIVE LOGITS
     hindsight
    0.93
     imprison
    0.74
     incarcer
    0.73
     spent
    0.69
     captivity
    0.68
     counting
    0.68
     adulthood
    0.67
     retrospect
    0.67
     matured
    0.67
    ét
    0.65
    Activations Density 0.153%

    No Known Activations