INDEX

Explanations

phrases that indicate a positive or affirmative condition

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

{{$

-0.81

 Mier

-0.74

 fhew

-0.73

 Pico

-0.73

CEN

-0.71

tdessen

-0.71

]="

-0.71

setConfig

-0.71

}<\

-0.70

DIO

-0.69

POSITIVE LOGITS

 well

0.82

 nahilalakip

0.77

 aswell

0.77

mybatisplus

0.74

 Well

0.71

väl

0.70

 تضيفلها

0.69

 Chwiliwch

0.69

 WELL

0.67

Väl

0.67

Activations Density 0.040%

phrases that indicate a positive or affirmative condition

No Comments

No Known Activations