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. 24379
    Prev
    Next
    INDEX
    Explanations

    dates written in the format "day month year"

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or references related to statistics or data points

    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
    enhagen
    -0.95
    orc
    -0.91
    ensed
    -0.79
    mble
    -0.78
    aired
    -0.76
     regenerate
    -0.75
    ovie
    -0.75
    odynamic
    -0.74
    onite
    -0.73
    odynam
    -0.71
    POSITIVE LOGITS
    rd
    0.88
    76
    0.87
    06
    0.85
    08
    0.82
    03
    0.79
    87
    0.79
    05
    0.79
    00
    0.78
    07
    0.78
    89
    0.77
    Activations Density 0.031%

    No Known Activations