INDEX

Explanations

phrases indicating actions or requests

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

CodeAttribute

-0.47

gento

-0.45

Abit

-0.44

 focal

-0.44

愁

-0.43

atro

-0.43

Decide

-0.42

Encourage

-0.41

UnitTesting

-0.41

 atra

-0.41

POSITIVE LOGITS

 view

0.97

 learn

0.94

CloseOperation

0.86

ंदीखरीदारी

0.85

 View

0.78

 download

0.77

 access

0.77

 VIEW

0.76

pushFollow

0.75

learn

0.72

Activations Density 0.171%

phrases indicating actions or requests

No Comments

No Known Activations