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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 8826
    Prev
    Next
    INDEX
    Explanations

    mentions of installations or installing things, such as solar panels or cameras

    oai_token-act-pair · gpt-3.5-turbo

    terms related to installation, particularly of solar panels and related equipment

    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
    sem
    -0.76
    furt
    -0.75
    razil
    -0.72
    bi
    -0.68
    externalActionCode
    -0.68
    fax
    -0.67
     Leth
    -0.67
    emic
    -0.67
    sweet
    -0.66
    zin
    -0.64
    POSITIVE LOGITS
     installations
    0.85
     installation
    0.82
     installs
    0.81
     ply
    0.79
     install
    0.76
     arrang
    0.75
     benches
    0.75
     installed
    0.75
     installing
    0.71
     fixtures
    0.70
    Activations Density 0.029%

    No Known Activations