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. 10-RES-JB
    6. 4161
    Prev
    Next
    INDEX
    Explanations

    information related to oil extraction, pipeline projects, and controversial drilling practices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chess
    -0.85
    amsung
    -0.84
    aternity
    -0.83
    omnia
    -0.82
    endars
    -0.81
     chess
    -0.78
     Weasley
    -0.77
     Psychiat
    -0.77
    ä¸ī
    -0.77
    thood
    -0.76
    POSITIVE LOGITS
     fracking
    1.83
     shale
    1.72
     drilling
    1.71
     pipelines
    1.56
     methane
    1.55
     pipeline
    1.51
     oil
    1.50
     Keystone
    1.45
     Pipeline
    1.42
     petroleum
    1.42
    Activations Density 0.589%

    No Known Activations