INDEX

Explanations

references to authors and titles in academic or research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

<()>

-0.44

begin

-0.41

突入

-0.41

たた

-0.40

jsonPath

-0.40

前景

-0.39

‘

-0.38

🧵

-0.38

 maneiras

-0.37

men

-0.36

POSITIVE LOGITS

 autorytatywna

1.26

 Roskov

1.06

Autoritní

1.04

 виправивши

1.02

期刊论文

1.01

:✨

1.00

 bezeichneter

1.00

 tartalomajánló

0.99

migrationBuilder

0.96

MLLoader

0.93

Activations Density 0.266%

references to authors and titles in academic or research contexts

No Comments

No Known Activations