INDEX

Explanations

references to the word "Great" and its variations in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

yntaxException

-0.57

-0.53

 gyvento

-0.53

FTFY

-0.53

ppuden

-0.53

 հղումներ

-0.52

ORCID

-0.52

 EClass

-0.52

Fonto

-0.51

 Wiktionnaire

-0.51

POSITIVE LOGITS

 deal

0.99

دانشنامهٔ

0.91

sword

0.85

deal

0.80

 deals

0.79

DEAL

0.78

 ddelweddau

0.77

 strides

0.75

great

0.73

Deal

0.73

Activations Density 0.046%

references to the word "Great" and its variations in text

No Comments

No Known Activations