INDEX

Explanations

Japanese characters and expressions related to events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

·

-0.47

-0.44

vy

-0.43

に着

-0.42

 के

-0.41

のス

-0.41

のコ

-0.40

 from

-0.40

のお店

-0.40

のア

-0.40

POSITIVE LOGITS

 itſelf

1.13

 AssemblyTitle

0.98

 myſelf

0.97

 Monfieur

0.96

 doubtnut

0.93

 crdi

0.90

 themſelves

0.87

 OnTriggerEnter

0.86

ſelves

0.86

interopRequire

0.85

Activations Density 0.150%

Japanese characters and expressions related to events or actions

No Comments

No Known Activations