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. 3799
    Prev
    Next
    INDEX
    Explanations

    time-related expressions such as durations and deadlines

    oai_token-act-pair · gpt-3.5-turbo

    time-related phrases and durations

    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
    acus
    -0.67
    Values
    -0.66
     hypocr
    -0.65
    ever
    -0.64
     Purg
    -0.61
    ramid
    -0.61
     Inher
    -0.61
    oren
    -0.61
    odium
    -0.59
    part
    -0.59
    POSITIVE LOGITS
    aneously
    0.88
     increments
    0.84
     confines
    0.81
     timeframe
    0.75
    eme
    0.75
     radius
    0.72
     vicinity
    0.69
     thereafter
    0.68
     intervals
    0.65
    strom
    0.65
    Activations Density 0.063%

    No Known Activations