INDEX

Explanations

references to historical events and timelines

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

NUMX

-0.98

 myſelf

-0.96

 itſelf

-0.95

 himſelf

-0.95

 Monfieur

-0.94

MENAFN

-0.93

 Majefty

-0.89

ſelves

-0.89

 themſelves

-0.88

 magasiner

-0.85

POSITIVE LOGITS

—

0.60

—

0.56

--

0.55

0.54

0.49

0.48

wärts

0.48

--

0.48

æ

0.48

ultimo

0.47

Activations Density 0.266%

references to historical events and timelines

No Comments

No Known Activations