INDEX

Explanations

instances of the word "cat."

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

findpost

-0.88

addCriterion

-0.69

 OFDb

-0.69

[*]

-0.61

 Económica

-0.60

\{\\

-0.59

 Alien

-0.57

protoc

-0.56

 bogotá

-0.56

transQ

-0.55

POSITIVE LOGITS

Mah

0.94

cat

0.83

Mah

0.71

 JpaRepository

0.62

mah

0.60

Zeneca

0.58

csolódó

0.58

data

0.58

TintMode

0.58

GraphicsUnit

0.58

Activations Density 0.168%

instances of the word "cat."

No Comments

No Known Activations