INDEX

Explanations

conversational phrases and terms indicating agreement or affirmation

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

 simplifié

-0.62

cierto

-0.55

anmoins

-0.55

 FEEDBACK

-0.54

égard

-0.54

Портали

-0.53

 Permalink

-0.52

---+

-0.52

 pagado

-0.52

 automatica

-0.49

POSITIVE LOGITS

Билгалдахарш

0.80

 kasarigan

0.75

makeConstraints

0.72

Cyfeiriadau

0.72

.*")]

0.68

AddTagHelper

0.63

Jeografia

0.61

 chi̍t

0.61

numerusform

0.60

 typelib

0.59

Activations Density 0.459%

conversational phrases and terms indicating agreement or affirmation

No Comments

No Known Activations