INDEX

Explanations

terms related to scientific or technical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Datuak

-0.84

 ویکی‌پدیا

-0.77

expandindo

-0.76

Geplaatst

-0.76

 AssemblyCulture

-0.74

Бахар

-0.65

CodeAttribute

-0.64

astéroïdes

-0.63

typeorm

-0.62

 linkovi

-0.62

POSITIVE LOGITS

 bande

0.51

(/^

0.48

kuuta

0.46

 superiore

0.46

stoma

0.46

imperial

0.45

 Kuan

0.45

 outs

0.44

rophe

0.43

lamydia

0.43

Activations Density 0.285%

terms related to scientific or technical concepts

No Comments

No Known Activations