INDEX

Explanations

coding-related elements like function definitions and button toggles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

parsedMessage

-1.20

 tartalomajánló

-1.15

ValueStyle

-1.09

IsContent

-1.09

 Monfieur

-1.06

LookAnd

-1.03

 myſelf

-1.03

Efq

-1.03

MigrationBuilder

-1.03

 Shakspeare

-1.02

POSITIVE LOGITS

FromArgb

0.89

toggle

0.75

0.64

0.62

0.61

of

0.60

for

0.55

вод

0.53

0.52

newcommand

0.52

Activations Density 0.020%

coding-related elements like function definitions and button toggles

No Comments

No Known Activations