INDEX

Explanations

repeated punctuation marks and numerical values

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

WebVitals

-0.67

-0.65

-0.63

awtextra

-0.60

ثيق

-0.57

 autorytatywna

-0.57

parsedMessage

-0.55

 يتيمه

-0.54

rungsseite

-0.54

POSITIVE LOGITS

hasOwnProperty

0.83

')['

0.73

 cauſe

0.65

toString

0.65

getProperty

0.64

(&:

0.63

get

0.62

get

0.61

 ſtand

0.60

Хьажоргаш

0.60

Activations Density 0.199%

repeated punctuation marks and numerical values

No Comments

No Known Activations