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. 16247
    Prev
    Next
    INDEX
    Explanations

    phrases related to timeliness and urgency

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to time management and promptness

    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
    rug
    -0.83
    aden
    -0.80
    wagen
    -0.79
    arov
    -0.78
    ramid
    -0.77
    bending
    -0.76
    ain
    -0.73
    erness
    -0.73
    Ring
    -0.73
    erie
    -0.73
    POSITIVE LOGITS
     timely
    0.91
     overdue
    0.80
     notifications
    0.78
    idious
    0.77
     warnings
    0.76
     delivery
    0.75
     showc
    0.75
    aneously
    0.75
     corrective
    0.73
     alerts
    0.73
    Activations Density 0.025%

    No Known Activations