INDEX

Explanations

references to programming languages, frameworks, and their built-in functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ValueStyle

-0.57

 mijne

-0.52

帖最后由

-0.50

 validamos

-0.49

ſcher

-0.49

 HFILL

-0.47

iNdEx

-0.47

 feroit

-0.45

Спољашње

-0.44

 tartalomajánló

-0.44

POSITIVE LOGITS

ftagPool

0.50

 built

0.43

 Microsoft

0.41

 tools

0.41

Built

0.38

Microsoft

0.38

 tool

0.38

 available

0.36

 Built

0.36

 BUILT

0.36

Activations Density 1.104%

references to programming languages, frameworks, and their built-in functionalities

No Comments

No Known Activations