INDEX

Explanations

comparative phrases that emphasize the highest or most significant attributes or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 BoxDecoration

-0.64

 autorytatywna

-0.63

IBOutlet

-0.59

illite

-0.57

ритори

-0.56

 PLWABN

-0.55

idiary

-0.52

providedIn

-0.51

něž

-0.50

Running

-0.49

POSITIVE LOGITS

FromArgb

0.60

❹

0.59

 least

0.59

 noqa

0.56

?}",

0.56

 maggior

0.55

 greatest

0.55

most

0.54

Least

0.53

richTextPanel

0.52

Activations Density 0.310%

comparative phrases that emphasize the highest or most significant attributes or occurrences

No Comments

No Known Activations