INDEX

Explanations

boolean values and related conditional statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mtd

-0.65

assing

-0.56

 paras

-0.55

ating

-0.55

 fossa

-0.54

cass

-0.54

meris

-0.54

Fod

-0.53

 bombard

-0.51

abag

-0.51

POSITIVE LOGITS

 true

1.13

 True

1.09

True

1.09

true

1.05

 TRUE

1.00

TRUE

0.91

 truer

0.74

assertTrue

0.73

 truest

0.71

 truth

0.70

Activations Density 0.131%

boolean values and related conditional statements

No Comments

No Known Activations