INDEX

Explanations

phrases relating to actions or activities involving "going" or "doing."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ffilm

-0.67

endcsname

-0.59

رشف

-0.58

}}}}

-0.57

erunner

-0.56

HasAnnotation

-0.55

صیلات

-0.52

\}_{

-0.52

CloseOperation

-0.52

?}",

-0.52

POSITIVE LOGITS

 school

1.10

 church

0.91

bed

0.90

 jail

0.86

 town

0.83

 court

0.82

 class

0.81

 camp

0.80

 skolan

0.75

 college

0.75

Activations Density 0.598%

phrases relating to actions or activities involving "going" or "doing."

No Comments

No Known Activations