INDEX

Explanations

phrases indicating quantity or frequency

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 starb

-0.74

AfterClass

-0.74

 closest

-0.68

μως

-0.67

 autorytatywna

-0.67

حوالہ

-0.65

 poveznice

-0.65

setVerticalGroup

-0.64

立った

-0.62

HandlerContext

-0.62

POSITIVE LOGITS

 lots

1.19

 many

1.16

Lots

1.12

 Lots

1.08

 alot

1.08

lot

1.07

 mucha

1.07

 banyak

1.01

Mucha

1.00

 lotta

0.99

Activations Density 0.137%

phrases indicating quantity or frequency

No Comments

No Known Activations