INDEX

Explanations

elements related to URLs and their components in code

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

 auffi

-0.58

 المعيارى

-0.56

 ſtate

-0.54

muerzo

-0.52

 ujednoznacz

-0.51

 obſ

-0.50

 preſ

-0.49

 faptul

-0.48

 raiſ

-0.48

 abſ

-0.48

POSITIVE LOGITS

forEach

0.95

 each

0.77

each

0.76

::~

0.69

Tracce

0.67

foreach

0.66

 EACH

0.65

SourceChecksum

0.65

 ویکی‌پدیا

0.65

">—

0.64

Activations Density 0.184%

elements related to URLs and their components in code

No Comments

No Known Activations