INDEX

Explanations

references to the concept of "gift."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

saraba

-0.66

rdquo

-0.64

GZIP

-0.55

zeň

-0.55

нент

-0.54

 squarely

-0.54

烃

-0.54

DataBind

-0.53

testens

-0.53

 suor

-0.53

POSITIVE LOGITS

 gift

1.11

 GIFT

1.04

 Gift

1.01

gift

0.97

GIFT

0.96

Gift

0.93

gif

0.91

 Gifts

0.84

 gifts

0.84

 gifted

0.81

Activations Density 0.080%

references to the concept of "gift."

No Comments

No Known Activations