INDEX

Explanations

references to data structures and operational commands in programming

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

 nonUne

-0.43

 Sanz

-0.41

 zape

-0.41

+#+#

-0.40

 menjalani

-0.39

 orchestrated

-0.39

ultati

-0.38

 Perrin

-0.38

 sprinkled

-0.37

())->

-0.37

POSITIVE LOGITS

protoimpl

0.49

setAccessible

0.47

 myſelf

0.47

StateToProps

0.45

QD

0.45

phosphat

0.44

 canst

0.43

gue

0.43

oflavin

0.43

MDL

0.42

Activations Density 1.349%

references to data structures and operational commands in programming

No Comments

No Known Activations