INDEX

Explanations

test-related keywords and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

}{@

-0.90

HasColumnType

-0.77

EDEFAULT

-0.75

HasMaxLength

-0.75

ConfigureAwait

-0.73

 <=",

-0.73

клопе

-0.72

awtextra

-0.72

contentLoaded

-0.71

 himo

-0.70

POSITIVE LOGITS

it

0.63

TestMethod

0.60

 useEffect

0.53

test

0.52

 Fact

0.47

 TestCase

0.47

 Ogni

0.46

onomia

0.45

describe

0.45

 test

0.45

Activations Density 0.112%

test-related keywords and structures

No Comments

No Known Activations