INDEX

Explanations

phrases indicating group involvement or collective identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

+#+#

-0.99

 utafitiHapana

-0.84

 فريبيس

-0.81

 الرياضيه

-0.76

Externé

-0.74

 виправивши

-0.72

tvguidetime

-0.71

 transfieras

-0.69

bootstrapcdn

-0.69

 елның

-0.68

POSITIVE LOGITS

 believe

0.71

believe

0.63

 anticipate

0.61

 constaté

0.61

 believes

0.61

 expect

0.60

 recognize

0.59

 reconhe

0.59

 reconoc

0.58

 commend

0.58

Activations Density 0.180%

phrases indicating group involvement or collective identity

No Comments

No Known Activations