INDEX

Explanations

references to 'hot' in various contexts

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

"hot" (and its translations)

np_acts-logits-general · gemini-2.0-flash

hot

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

󠁢

-0.67

iastes

-0.65

 MainAxisSize

-0.64

 CreateTagHelper

-0.63

évaluateur

-0.62

rénées

-0.61

alion

-0.60

rhosis

-0.60

 تانيه

-0.57

ajuato

-0.57

POSITIVE LOGITS

hot

1.19

Hot

1.14

Hot

1.13

HOT

1.11

HOT

1.07

hot

1.06

 hotter

0.93

 hottest

0.89

shot

0.71

 scorching

0.68

Activations Density 0.033%

references to 'hot' in various contexts

"hot" (and its translations)

hot

No Comments

No Known Activations