© 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. 20510
    Prev
    Next
    INDEX
    Explanations

    the name "Cook"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' names and associated actions or responsibilities

    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
     Circle
    -0.79
     NX
    -0.78
     opposite
    -0.77
     RX
    -0.77
     oversized
    -0.75
     hallucinations
    -0.72
     nightmares
    -0.71
     heroine
    -0.70
     alumni
    -0.70
     phantom
    -0.70
    POSITIVE LOGITS
    Cook
    2.73
    Govern
    2.11
    Smith
    2.09
    cook
    1.68
    Stew
    1.56
    Park
    1.44
    Interest
    1.42
    Java
    1.37
    Iv
    1.37
    Hunt
    1.36
    Activations Density 0.043%

    No Known Activations