© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 4759
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Shell"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "Shell."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     af
    -0.82
     disorder
    -0.70
     proportion
    -0.69
     epile
    -0.69
     infringing
    -0.69
    âĺ
    -0.69
    abilia
    -0.67
    weeney
    -0.66
    ðŁij
    -0.65
    trained
    -0.65
    POSITIVE LOGITS
     Shell
    4.12
    Shell
    2.88
    shell
    1.91
     Chevron
    1.77
     shell
    1.69
     shells
    1.58
     Exxon
    1.25
     BP
    1.17
     Oil
    1.08
     Mobil
    1.07
    Activations Density 0.024%

    No Known Activations