INDEX

Explanations

discourse markers that indicate speculation or conditionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

tagHelperRunner

-0.69

SequentialGroup

-0.64

cyklopedia

-0.57

檚

-0.56

Literatuur

-0.56

 المعيارى

-0.53

 endblock

-0.52

 getM

-0.51

swire

-0.50

TestData

-0.49

POSITIVE LOGITS

 Мексичка

0.77

GEBURTS

0.65

 Taktlose

0.60

Sucesor

0.60

FunctionFlags

0.59

❋

0.59

 myſelf

0.58

EnumMember

0.56

LogFactory

0.56

✎

0.56

Activations Density 0.340%

discourse markers that indicate speculation or conditionality

No Comments

No Known Activations