INDEX

Explanations

statistical significance in research results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Larger

-0.80

(>

-0.78

 Larger

-0.77

 الحره

-0.76

larger

-0.74

 larger

-0.72

 bigger

-0.71

|>

-0.69

Higher

-0.69

 Bigger

-0.69

POSITIVE LOGITS

 less

1.92

 Less

1.61

Less

1.47

 moins

1.45

 menos

1.36

 LESS

1.35

 lesser

1.28

 fewer

1.27

less

1.24

 weniger

1.16

Activations Density 1.132%

statistical significance in research results

No Comments

No Known Activations