INDEX

Explanations

references to "hot" in various contexts, particularly in relation to physical temperatures or trending topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

quelize

-0.74

 MainAxisSize

-0.73

Bronnen

-0.68

vriende

-0.65

initializeApp

-0.63

 setInterval

-0.62

 adiós

-0.62

ställning

-0.61

 resourceCulture

-0.61

 Watches

-0.61

POSITIVE LOGITS

hot

0.95

HOT

0.90

Hot

0.87

Hot

0.83

HOT

0.83

hot

0.77

shot

0.73

dog

0.64

rod

0.63

rod

0.62

Activations Density 0.049%

references to "hot" in various contexts, particularly in relation to physical temperatures or trending topics

No Comments

No Known Activations