INDEX

Explanations

terms related to medical or scientific research, particularly those associated with antidepressants and their effects

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

"ant" followed by certain letters

np_acts-logits-general · gemini-2.0-flash

Gigant Houoh

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ed

-0.92

eyes

-0.87

ear

-0.78

eye

-0.77

away

-0.76

istered

-0.75

 Czer

-0.73

Autoritní

-0.71

 referenties

-0.71

höhung

-0.71

POSITIVE LOGITS

ant

1.02

ort

0.84

ANT

0.81

ult

0.81

ent

0.81

tant

0.80

est

0.80

EMENT

0.75

ont

0.74

vent

0.74

Activations Density 0.863%

terms related to medical or scientific research, particularly those associated with antidepressants and their effects

"ant" followed by certain letters

Gigant Houoh

No Comments

No Known Activations