Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15450
    Prev
    Next
    INDEX
    Explanations

    timestamps in specific formats

    oai_token-act-pair · gpt-3.5-turbo

    timestamps or date-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orno
    -0.77
    chwitz
    -0.74
    orc
    -0.73
     destro
    -0.67
    ersen
    -0.66
     balcon
    -0.64
     envelop
    -0.62
     extermin
    -0.60
    undai
    -0.59
    uctor
    -0.59
    POSITIVE LOGITS
     UTC
    0.91
     GMT
    0.88
    UTC
    0.86
     msec
    0.86
    th
    0.81
     mins
    0.77
     EDT
    0.76
     minutes
    0.76
     Minutes
    0.76
    pm
    0.75
    Activations Density 0.068%

    No Known Activations