INDEX

Explanations

references or citations related to research metrics or data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

الحياه

-0.86

 BoxDecoration

-0.69

الإنجليزية

-0.67

Rujuakan

-0.62

曖昧さ回避

-0.62

tahui

-0.60

tvguidetime

-0.59

NameInMap

-0.59

ByPrimaryKey

-0.58

 StringTokenizer

-0.58

POSITIVE LOGITS

 Ebook

0.52

__'

0.48

UrlResolution

0.44

könyv

0.43

cology

0.42

hibi

0.42

']))

0.41

menea

0.41

 printed

0.41

();)

0.40

Activations Density 0.131%

references or citations related to research metrics or data

No Comments

No Known Activations