INDEX

Explanations

specific keywords and phrases that indicate actions and processes within 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.82

.”

-0.65

。

-0.63

”.

-0.62

}$.

-0.59

".

-0.57

."

-0.56

 الحره

-0.56

».

-0.55

$.

-0.55

POSITIVE LOGITS

 EconPapers

0.79

ówczas

0.78

Hochspringen

0.73

 mxArray

0.72

mybatisplus

0.71

 betweenstory

0.70

 chi̍t

0.69

styleUrls

0.64

 Мексичка

0.64

 transférez

0.64

Activations Density 0.697%

specific keywords and phrases that indicate actions and processes within various contexts

No Comments

No Known Activations