INDEX

Explanations

phrases indicating conditions or contexts that prompt discussions or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Normandy

-0.85

 Normandie

-0.74

 AppColors

-0.73

 sentimenti

-0.72

 Orozco

-0.70

 tasche

-0.68

صرية

-0.68

 Kathy

-0.67

Unsubscribe

-0.66

 Jerry

-0.65

POSITIVE LOGITS

 Given

1.38

 given

1.29

Given

1.25

given

1.11

iven

1.10

 GIVEN

1.01

Dado

0.98

 dado

0.91

 Dado

0.90

yntaxException

0.87

Activations Density 0.157%

phrases indicating conditions or contexts that prompt discussions or conclusions

No Comments

No Known Activations