INDEX

Explanations

formatting and structural components commonly found in programming or technical documentation

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

 Numerade

-0.80

 ligiloj

-0.77

 '\\;'

-0.73

 EnglishChoose

-0.73

}],

-0.71

 }}}{

-0.69

 Paglinawan

-0.68

 виправивши

-0.68

wortet

-0.67

 onCancelled

-0.67

POSITIVE LOGITS

 AppModule

0.54

 IEnumerator

0.52

andafter

0.52

 glaube

0.49

 confirmer

0.49

IEnumerator

0.48

ثمان

0.48

 taşı

0.48

Traceback

0.47

tahankan

0.46

Activations Density 0.021%

formatting and structural components commonly found in programming or technical documentation

No Comments

No Known Activations