INDEX

Explanations

pronouns used to refer to people or things in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 vált

-0.59

 kuiten

-0.57

 spurs

-0.56

دواج

-0.55

 diyor

-0.55

 médicaux

-0.54

 Looking

-0.54

 Debido

-0.54

 stalo

-0.54

 kuitenkin

-0.54

POSITIVE LOGITS

 &___

0.80

)");

0.79

0.78

 محفوظة

0.76

'],

0.74

'}>

0.72

 ThemeData

0.71

 auquel

0.71

PageContext

0.71

 Thon

0.71

Activations Density 0.117%

pronouns used to refer to people or things in a text

No Comments

No Known Activations