INDEX

Explanations

titles or headings in academic documents

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

 myſelf

-0.58

 contextLoads

-0.56

μφωνα

-0.53

 Avez

-0.53

nextSibling

-0.52

UserScript

-0.50

onAttach

-0.50

تقاوى

-0.49

 fevere

-0.49

berdayakan

-0.49

POSITIVE LOGITS

QMetaType

0.65

ISupport

0.64

 jScrollPane

0.59

WithIOException

0.58

roughs

0.57

rungen

0.56

下载附件

0.55

0.54

downarrow

0.54

Activations Density 1.418%

titles or headings in academic documents

No Comments

No Known Activations