INDEX

Explanations

assertions and claims about truth and belief

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rophoresis

-0.65

haustible

-0.64

UnusedPrivate

-0.63

tyard

-0.58

setViewportView

-0.58

ритори

-0.57

/\.

-0.56

цезда

-0.55

.*")]

-0.55

hyrchwyd

-0.55

POSITIVE LOGITS

 itſelf

0.66

 somewhat

0.58

(),

0.57

 Dennoch

0.57

 MainAxisSize

0.56

Rüyada

0.55

 poffible

0.55

 fufficient

0.53

 meis

0.53

 nominally

0.52

Activations Density 0.293%

assertions and claims about truth and belief

No Comments

No Known Activations