INDEX

Explanations

sentences and punctuation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ***!

-0.77

 autorytatywna

-0.73

 Wicidata

-0.70

Collegamenti

-0.69

NKC

-0.64

Зноскі

-0.64

Extinguishing

-0.62

QMetaType

-0.61

 Answer

-0.59

 مواليد

-0.59

POSITIVE LOGITS

println

1.13

 println

0.83

print

0.79

 print

0.66

printf

0.64

prin

0.59

format

0.59

Print

0.55

 printers

0.55

prit

0.55

Activations Density 0.019%

sentences and punctuation

No Comments

No Known Activations