INDEX

Explanations

instances of the word "even"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

TagMode

-0.75



-0.70

ImageContext

-0.68

+#+#

-0.64

انيف

-0.60

DebuggerNonUser

-0.59

帖最后由

-0.58

requireNonNull

-0.57

 disambiguazione

-0.55

parsedMessage

-0.55

POSITIVE LOGITS

 كومونز

0.63

tagHelper

0.56

 aman

0.54

即使

0.54

 Malgré

0.54

oore

0.53

即便是

0.53

 despite

0.52

#__

0.52

 Superstar

0.51

Activations Density 0.073%

instances of the word "even"

No Comments

No Known Activations