INDEX

Explanations

instances of the word "called."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.56

amaño

-0.51

 '/';

-0.49

reportWebVitals

-0.47

PointSize

-0.46

 Houſe

-0.46

 biol

-0.46

 BASF

-0.45

 Accesat

-0.44

Legături

-0.44

POSITIVE LOGITS

 CALLED

0.99

 called

0.95

called

0.93

Called

0.83

 Called

0.83

UnknownFieldSet

0.80

“

0.79

 bernama

0.77

叫做

0.77

 nicknamed

0.75

Activations Density 0.135%

instances of the word "called."

No Comments

No Known Activations