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. 18832
    Prev
    Next
    INDEX
    Explanations

    temporal events or moments in time

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "just before" followed by various times referenced in a narrative or chronological context

    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
    vari
    -0.82
    uph
    -0.76
    alian
    -0.74
    atis
    -0.70
    uity
    -0.67
    alam
    -0.67
    Helper
    -0.65
    amen
    -0.65
    orers
    -0.63
    bats
    -0.62
    POSITIVE LOGITS
    çͰ
    0.72
     Azerb
    0.67
     coast
    0.66
    onday
    0.65
     sunrise
    0.65
     Christmas
    0.63
     Interstate
    0.63
     Mellon
    0.62
    undown
    0.60
     clipping
    0.60
    Activations Density 0.060%

    No Known Activations