INDEX

Explanations

code snippets and data structure definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 nakalista

-1.18

PhysRevD

-1.07

 EconPapers

-1.01

 estimés

-1.00

windowFixed

-0.98

oredCriteria

-0.96

Datuak

-0.95

verifyException

-0.93

 pinulongan

-0.90

IsContent

-0.90

POSITIVE LOGITS

0.48

↵

0.46

0.41

0.40

).

0.39

 just

0.37

 rather

0.37

Activations Density 0.600%

code snippets and data structure definitions

No Comments

No Known Activations