INDEX

Explanations

patterns related to formatting and structure in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

tagHelperRunner

-1.24

Personendaten

-1.18

 مرئيه

-1.14

 Paglinawan

-1.10

InjectAttribute

-1.05

تقاوى

-1.04

ьаж

-1.02

ſelves

-1.01

Jereo

-1.00

 Roskov

-0.99

POSITIVE LOGITS

↵

0.71

0.68

↵↵

0.65

“

0.61

…

0.61

“

0.60

0.58

</i>

0.58

0.52

...

0.52

Activations Density 0.642%

patterns related to formatting and structure in text

No Comments

No Known Activations