INDEX

Explanations

negative sentiments or conditions related to health and mortality

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

 Censo

-0.70

الدراسه

-0.61

MessageOf

-0.61

 تضيفلها

-0.60

 oocytes

-0.59

ようになりました

-0.56

Cyfeiriadau

-0.56

 متعلقه

-0.56

PullParser

-0.56

 locul

-0.55

POSITIVE LOGITS

neſs

0.74

 Majefty

0.60

 Chriftian

0.58

 Jefus

0.58

 Мексичка

0.58

‌ترین

0.57

 Monfieur

0.55

 ترین

0.55

ombie

0.54

 ſeveral

0.54

Activations Density 0.661%

negative sentiments or conditions related to health and mortality

No Comments

No Known Activations