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. 1261
    Prev
    Next
    INDEX
    Explanations

    terms related to firmware and software updates

    oai_token-act-pair · gpt-3.5-turbo

    references to firmware and software related to hacking or modification of devices

    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
    ivas
    -0.94
    bilt
    -0.85
    incerity
    -0.82
    lasses
    -0.80
    throp
    -0.80
    riers
    -0.78
    orem
    -0.77
    cas
    -0.76
    rina
    -0.76
    race
    -0.75
    POSITIVE LOGITS
     firmware
    1.15
     installer
    0.91
     ROM
    0.90
     BIOS
    0.88
     tweak
    0.87
     patched
    0.82
     modification
    0.79
     update
    0.79
     flashing
    0.78
     compatibility
    0.78
    Activations Density 0.062%

    No Known Activations