INDEX

Explanations

references to integration and augmentation within systems or processes

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

mo

-0.55

Bibliograf

-0.47

理石

-0.45

롬

-0.45

Autoritní

-0.45

ngày

-0.44

#![

-0.43

턴

-0.43

set

-0.42

出版年

-0.42

POSITIVE LOGITS

 existing

1.03

Existing

1.02

existing

1.00

既存

0.99

 Existing

0.98

 bestehende

0.94

 EXISTING

0.88

 bestaande

0.84

 bestehenden

0.81

 existente

0.81

Activations Density 0.386%

references to integration and augmentation within systems or processes

No Comments

No Known Activations