INDEX

Explanations

instances of the word "show" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Brito

-0.75

Spacing

-0.69

 Balt

-0.67

 lèvres

-0.65

zünd

-0.65

延伸閱讀

-0.63

 Petra

-0.63

 labios

-0.62

 funcionales

-0.60

 peligros

-0.60

POSITIVE LOGITS

 shows

2.70

 show

2.65

 Shows

2.64

 showing

2.60

 Showing

2.57

shows

2.55

 SHOW

2.49

Shows

2.48

 SHOWING

2.47

SHOW

2.46

Activations Density 0.126%

instances of the word "show" in various forms

No Comments

No Known Activations