INDEX

Explanations

references to environment and system components in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ویکی‌پدی

-0.52

parsedMessage

-0.51

ScopeManager

-0.48

 Normdatei

-0.47

oa̍t

-0.43

 мәкал

-0.43

 kaarangay

-0.42

IVEREF

-0.42

 ویکی‌پدیا

-0.41

onOptions

-0.41

POSITIVE LOGITS

seamnă

0.51

 "..\..\

0.48



0.45

 dago

0.44

 "..\..\..\

0.44

jarse

0.43

Everything

0.42

INUM

0.42

 Sünde

0.42

Orang

0.42

Activations Density 1.095%

references to environment and system components in a coding context

No Comments

No Known Activations