INDEX

Explanations

terms related to knowledge and awareness

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArrowToggle

-0.74

esgue

-0.73

fjspx

-0.72

 gyhoeddwyd

-0.71

AccessorTable

-0.69

CompleteListener

-0.68

 dAtA

-0.68

tagHelperRunner

-0.67

 Савезне

-0.66

 Shakspeare

-0.64

POSITIVE LOGITS

 know

1.78

 knows

1.76

know

1.69

Know

1.57

knows

1.56

 Know

1.52

 Knows

1.49

 knew

1.48

 knowing

1.46

 KNOW

1.43

Activations Density 0.340%

terms related to knowledge and awareness

No Comments

No Known Activations