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. 3912
    Prev
    Next
    INDEX
    Explanations

    specific time indications

    oai_token-act-pair · gpt-3.5-turbo

    specific time references in the context of schedules or events

    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
    Reviewer
    -0.65
     DRAG
    -0.64
     cheated
    -0.64
     abbre
    -0.62
     forgiven
    -0.62
     faster
    -0.62
     portrayed
    -0.61
     worthless
    -0.61
     acronym
    -0.61
     gimmick
    -0.59
    POSITIVE LOGITS
    nm
    1.03
    th
    1.02
    pm
    0.97
    °
    0.91
    89
    0.91
    ½
    0.90
     Minutes
    0.90
    eenth
    0.89
    aturdays
    0.89
    09
    0.89
    Activations Density 0.200%

    No Known Activations