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. 12-RES-JB
    6. 15221
    Prev
    Next
    INDEX
    Explanations

    URLs and technical data related to Earth observatories and astronomical images

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

    references to visual content and documentation

    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
    olon
    -0.79
    fifth
    -0.67
    ency
    -0.67
    ingo
    -0.63
    amn
    -0.62
     welf
    -0.61
    amount
    -0.59
    eny
    -0.59
     Root
    -0.56
     rall
    -0.56
    POSITIVE LOGITS
    hov
    0.84
    AGES
    0.66
     Planetary
    0.66
    sov
    0.66
    lasses
    0.65
    antage
    0.63
    rius
    0.61
    nova
    0.60
    åĤ
    0.60
    YE
    0.59
    Activations Density 0.095%

    No Known Activations