© 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. 1-RES-JB
    11. 20048
    Prev
    Next
    INDEX
    Explanations

    names or terms related to McKinsey, a global management consulting firm

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the consulting firm McKinsey and associated names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.84
     Gravity
    -0.72
    λ
    -0.72
    spring
    -0.70
     Pixie
    -0.70
    ι
    -0.69
    ÏĦ
    -0.69
    ItemTracker
    -0.69
    âĢ¢âĢ¢
    -0.66
    ãĥł
    -0.65
    POSITIVE LOGITS
    ney
    1.02
    nea
    1.00
     McKin
    0.98
    sey
    0.96
    neys
    0.92
    iets
    0.86
    intosh
    0.86
    ners
    0.84
    ufact
    0.81
    seys
    0.81
    Activations Density 0.006%

    No Known Activations