INDEX

Explanations

tokens related to data structure and formatting

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

brainly

-0.52

gwt

-0.47

">//

-0.46

 balance

-0.45

‘

-0.45

 change

-0.44

gmx

-0.44

bazel

-0.43

PHPExcel

-0.43

 маса

-0.43

POSITIVE LOGITS

 ujednoznacz

0.89

 IEEE

0.86

\{\\

0.81

RenderAtEndOf

0.81

IEEE

0.78

 sows

0.77

 كومونز

0.76

 تضيفلها

0.75

 anhyd

0.74

 Sodom

0.73

Activations Density 1.010%

tokens related to data structure and formatting

No Comments

No Known Activations