INDEX

Explanations

mentions of the term "dom" in various contexts

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

ValueStyle

-0.86

참고

-0.76

 متعلقه

-0.74

ècie

-0.69

 itſelf

-0.65

Билгалдахарш

-0.64

AutoScale

-0.64

 reaſon

-0.63

évaluateur

-0.62

 octavia

-0.62

POSITIVE LOGITS

dom

3.47

dom

3.00

Dom

2.99

Dom

2.91

DOM

2.81

DOM

2.69

doms

2.16

 Domes

1.47

dome

1.47

 domes

1.44

Activations Density 0.047%

mentions of the term "dom" in various contexts

No Comments

No Known Activations