INDEX

Explanations

words that express skepticism or questioning sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

})`

-0.67

rmızı

-0.64

♂

-0.63

>`;

-0.62

 ergo

-0.62

DTC

-0.61

HRC

-0.60

}))

-0.60

EDC

-0.59

 nahilalakip

-0.59

POSITIVE LOGITS

 barely

0.72

 nemmeno

0.69

 siquiera

0.68

 even

0.66

 Even

0.61

 &___

0.59

すら

0.56

apimachinery

0.56

 Olímpicos

0.56

 Just

0.55

Activations Density 0.085%

words that express skepticism or questioning sentiment

No Comments

No Known Activations