INDEX

Explanations

sequences of numerical values or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Бли

-0.67

bule

-0.66

istic

-0.66

گذ

-0.64

ので

-0.62

一个

-0.62

vle

-0.61

ள்

-0.60

bege

-0.59

dza

-0.59

POSITIVE LOGITS

1.75

 NINE

1.26

 Ninth

1.18

nine

1.17

 ninth

1.11

 ninety

1.10

ninth

1.10

۹

1.10

 nueve

1.07

 Phry

1.06

Activations Density 0.761%

sequences of numerical values or identifiers

No Comments

No Known Activations