INDEX

Explanations

phrases indicating purpose or intention

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

 Jefus

-0.95

 poffible

-0.89

ſelf

-0.88

 myſelf

-0.88

 themſelves

-0.87

 ſeveral

-0.86

 Anſ

-0.86

 Theſe

-0.83

 Monfieur

-0.83

 chofe

-0.80

POSITIVE LOGITS

be

0.67

re

0.57

}}</

0.56

daß

0.55

dynam

0.55

)':

0.55

 ולה

0.53

'><

0.53

tidae

0.53

}{#

0.52

Activations Density 0.172%

phrases indicating purpose or intention

No Comments

No Known Activations