INDEX

Explanations

quantifiers and inclusive terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

+#+#

-0.57

 pitch

-0.42

jetbrains

-0.41

 hidrá

-0.41

 continuación

-0.41

 Jangan

-0.40

Portail

-0.40

 dommage

-0.39

 okuyayım

-0.38

ССР

-0.38

POSITIVE LOGITS

 utafitiHapana

0.78

setVerticalGroup

0.76

`{.

0.75

 ब्रेकडाउन

0.75

()");

0.73

Koordinaten

0.72

 odkazy

0.71

\"></

0.70

+:+

0.70

twimg

0.70

Activations Density 0.353%

quantifiers and inclusive terms

No Comments

No Known Activations