INDEX

Explanations

boolean values or statements that evaluate to true.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

boolean expressions and true/false evaluations.

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

mathematical equations and conditions being evaluated for true or false statements.

oai_token-act-pair · gpt-3.5-turbo 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

 insuffisamment

-0.68

yntaxException

-0.64

Activités

-0.62

etera

-0.61

pshots

-0.59

 Vedi

-0.58

einem

-0.58

DeleteBehavior

-0.58

 يتيمه

-0.57

__*/

-0.57

POSITIVE LOGITS

False

0.88

 False

0.87

stdbool

0.83

false

0.73

 false

0.73

 True

0.66

TRUE

0.66

beginPath

0.66

FALSE

0.65

 FALSE

0.64

Activations Density 0.050%

boolean values or statements that evaluate to true.

boolean expressions and true/false evaluations.

mathematical equations and conditions being evaluated for true or false statements.

No Comments

No Known Activations