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. 17744
    Prev
    Next
    INDEX
    Explanations

    instructions related to downloading and installing software updates

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

    terms related to software installation and updates

    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
    ablishment
    -0.77
    death
    -0.73
    chairs
    -0.73
    Ĭ±
    -0.72
    Í
    -0.71
    manship
    -0.70
    iatus
    -0.70
    ulence
    -0.68
     distinction
    -0.67
    ativity
    -0.67
    POSITIVE LOGITS
     installer
    1.14
     software
    1.10
     firmware
    1.09
     Drivers
    0.99
     zip
    0.97
     drivers
    0.96
     binaries
    0.93
     ZIP
    0.91
     executable
    0.89
     downloaded
    0.89
    Activations Density 0.289%

    No Known Activations