INDEX

Explanations

mathematical notations and symbols used in formal equations and expressions

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

-0.73

-0.63

cente

-0.60

).

-0.57

-0.56

 normally

-0.56

-0.55

-0.54

POSITIVE LOGITS

tagHelperRunner

1.16

enumi

1.01

 myſelf

1.01

 Monfieur

1.00

 reaſon

0.95

 Reſ

0.94

Efq

0.94

 purpoſe

0.92

 ſeveral

0.89

 betweenstory

0.88

Activations Density 0.326%

mathematical notations and symbols used in formal equations and expressions

No Comments

No Known Activations