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. 12-RES-JB
    6. 14542
    Prev
    Next
    INDEX
    Explanations

    words related to fine-tuning and precision

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to quality or precision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itals
    -0.69
    ãĤª
    -0.69
    leaders
    -0.69
    ucer
    -0.66
    acles
    -0.66
    other
    -0.66
    edes
    -0.64
    ob
    -0.63
    olver
    -0.63
    ational
    -0.62
    POSITIVE LOGITS
     tuning
    1.12
     tuned
    1.09
     Gael
    1.02
     dining
    0.99
     arts
    0.96
     print
    0.91
     tune
    0.90
    tun
    0.88
     Print
    0.84
     distinctions
    0.81
    Activations Density 0.056%

    No Known Activations