INDEX

Explanations

Java class and method definitions

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

+#+#

-0.60

ksesta

-0.53

oa̍t

-0.53

 הזה

-0.52

 becauſe

-0.51

⏟

-0.51

ECAUSE

-0.50

 secco

-0.50

 supo

-0.50

定了

-0.50

POSITIVE LOGITS

 main

2.26

main

2.18

Main

1.82

 Main

1.74

 MAIN

1.67

MAIN

1.66

 Haupt

1.34

メイン

1.31

主

1.29

getMain

1.22

Activations Density 0.154%

Java class and method definitions

No Comments

No Known Activations