INDEX

Explanations

terms related to medical conditions and emergencies, specifically involving the heart and brain

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FTFY

-0.68

TintMode

-0.68

 оригіналу

-0.67

DoubleQuotes

-0.64

MigrationBuilder

-0.62

mergeFrom

-0.62

elson

-0.61

cinogenicity

-0.61

 interconnection

-0.60

 Administrativna

-0.59

POSITIVE LOGITS

 attack

1.05

 attacks

0.96

 episode

0.89

 ataque

0.85

 episodes

0.85

 crisi

0.85

 attaque

0.85

 seizure

0.84

attack

0.83

 crise

0.82

Activations Density 0.344%

terms related to medical conditions and emergencies, specifically involving the heart and brain

No Comments

No Known Activations