INDEX

Explanations

actions related to user permissions and interactions with data

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

 autorytatywna

-0.87

 مرئيه

-0.83

 دیکھیے

-0.77

 ***!

-0.73

 prisonniers

-0.71

 NSCoder

-0.71

=$?

-0.70

 Wikimedijinoj

-0.70

таратура

-0.70

struzioni

-0.69

POSITIVE LOGITS

 ולה

0.66

\{\\

0.59

 utilizing

0.46

 ול

0.44

multirow

0.44

UnusedPrivate

0.43

0.42

decer

0.42

“

0.41

âni

0.41

Activations Density 0.848%

actions related to user permissions and interactions with data

No Comments

No Known Activations