INDEX

Explanations

list items in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AccessorTable

-0.83

Geplaatst

-0.75

 дописавши

-0.60

jooq

-0.60

XmlSchema

-0.59

copia

-0.59

IPAC

-0.58

 Reiche

-0.57

ARAN

-0.57

ViewFeatures

-0.56

POSITIVE LOGITS

li

2.70

li

1.67

Li

1.52

LI

1.51

Li

1.43

LI

1.11

liwości

1.03

lii

0.90

liy

0.87

lı

0.84

Activations Density 0.036%

list items in a document

No Comments

No Known Activations