INDEX

Explanations

references to studies and research related content

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

 Waray

-0.56

 استنادى

-0.54

Alike

-0.53

>[]

-0.50

Extinguishing

-0.50

 Administrativna

-0.48

 виправивши

-0.47

("</

-0.47

Caratteristiche

-0.45

 lenker

-0.45

POSITIVE LOGITS

 raiſ

0.65

RetentionPolicy

0.63

segno

0.61

writeFieldEnd

0.59

XmlType

0.58

UnusedPrivate

0.57

Referencie

0.57

 itſelf

0.57

BagConstraints

0.56

owanego

0.56

Activations Density 0.702%

references to studies and research related content

No Comments

No Known Activations