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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 10887
    Prev
    Next
    INDEX
    Explanations

    numerical references to the 21st century

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 21 and its significance in various contexts

    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
    ensional
    -0.89
    apers
    -0.81
    UFF
    -0.79
    aped
    -0.79
    akable
    -0.75
    outed
    -0.72
    akespe
    -0.72
    plom
    -0.72
    qqa
    -0.72
    chio
    -0.71
    POSITIVE LOGITS
    st
    1.03
    50
    0.82
    00
    0.78
    nd
    0.74
    IST
    0.74
    ists
    0.74
    nect
    0.74
    hole
    0.71
    xus
    0.71
    rd
    0.71
    Activations Density 0.033%

    No Known Activations