INDEX

Explanations

the occurrence of the word "as" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 autorytatywna

-0.74

bibinfo

-0.69

BibitemShut

-0.68

ongiorno

-0.67

edì

-0.67

adpleegd

-0.66

ellini

-0.66

iffance

-0.66

/−

-0.66

iterranean

-0.65

POSITIVE LOGITS

as

3.41

AS

1.78

As

1.74

asnya

1.68

As

1.41

as

1.40

AS

1.26

asun

1.13

как

0.97

asn

0.95

Activations Density 0.073%

the occurrence of the word "as" in various contexts

No Comments

No Known Activations