INDEX

Explanations

discourse markers and verbs indicating past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.84

󠁢

-0.76

 unprotected

-0.66

URLEncoder

-0.65

 houſe

-0.65

 Chriftian

-0.63

 Gable

-0.63

 igång

-0.63

 purpoſe

-0.63

ɫ

-0.63

POSITIVE LOGITS

is

0.75

 will

0.74

XmlAccessType

0.71

 certainly

0.68

 also

0.68

may

0.67

has

0.64

not

0.60

 propOrder

0.59

was

0.58

Activations Density 0.927%

discourse markers and verbs indicating past events

No Comments

No Known Activations