INDEX

Explanations

specific identifiers related to educational categories and unique items in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinulongan

-0.84

 Мексичка

-0.83

 Савезне

-0.78

 snippetHide

-0.76

InjectAttribute

-0.76

ftagPool

-0.74

kháu

-0.74

 оригіналу

-0.73

новниш

-0.73

SBATCH

-0.68

POSITIVE LOGITS

 Walkover

0.47

べ

0.46

'{

0.43

 Hahn

0.43

Am

0.42

''

0.42

ए

0.41

Activations Density 0.280%

specific identifiers related to educational categories and unique items in a structured context

No Comments

No Known Activations