INDEX

Explanations

quantitative measurements and numerical values

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

 فريبيس

-1.01

StoreMessageInfo

-1.00

ViewFeatures

-0.95

 виправивши

-0.91

 resourceCulture

-0.89

Дереккөздер

-0.87

 متعلقه

-0.85

fjspx

-0.85

 للمعارف

-0.83

__':

-0.82

POSITIVE LOGITS

0.55

↵↵

0.53

“

0.47

0.45

笈

0.44

↵

0.42

op

0.41

‘

0.41

 Thomas

0.40

Activations Density 0.762%

quantitative measurements and numerical values

No Comments

No Known Activations