INDEX

Explanations

occurrences of actions or requests involving communication or advisement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

cellaneous

-0.61

"]));

-0.61

]){

-0.60

atrième

-0.59

 Italijanski

-0.58

cosity

-0.58

λιο

-0.58

 Réponses

-0.57

HomeAsUp

-0.56

uracy

-0.56

POSITIVE LOGITS

ModelAdmin

0.58

RequestParam

0.53

存于互联网档案馆

0.53

让他们

0.51

CopyWith

0.50

 onAnimation

0.49

 pergunt

0.48

Ằ

0.48

 diven

0.47

 vocale

0.46

Activations Density 0.283%

occurrences of actions or requests involving communication or advisement

No Comments

No Known Activations