INDEX

Explanations

instances of the word "plain."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 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

 Autorizaciones

-0.69

LookAnd

-0.64

 XCTest

-0.62

CloseHandle

-0.60

ѓ

-0.60

+#+#

-0.58

clientY

-0.57

DebuggerNonUser

-0.56

bufio

-0.56

 Utilizamos

-0.56

POSITIVE LOGITS

 plain

0.92

 Plain

0.87

gmail

0.72

Chart

0.68

Plain

0.68

 оригіналу

0.66

 Market

0.64

 Chart

0.63

plain

0.62

JsonFormat

0.60

Activations Density 0.278%

instances of the word "plain."

No Comments

No Known Activations