INDEX

Explanations

terms related to serialization and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aarrggbb

-0.44

SLC

-0.42

SLC

-0.37

 ब्रेकडाउन

-0.37

yyj

-0.36

########.

-0.35

 Avon

-0.35

HLA

-0.35

 iprot

-0.34

 Bigg

-0.34

POSITIVE LOGITS

Leo

0.64

Leo

0.61

 aero

0.60

 battery

0.60

 Jerry

0.59

 TREAS

0.59

treasure

0.58

aero

0.57

 treasure

0.57

Jerry

0.57

Activations Density 0.356%

terms related to serialization and data structures

No Comments

No Known Activations