INDEX

Explanations

negative sentiments about stories or movies

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

Tokens preceding negative conjunctions

np_acts-logits-general · gemini-2.0-flash

negative outcomes

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

-0.57

Agreg

-0.52

 mengenal

-0.49

 ISTAT

-0.48

 conoscere

-0.48

entennial

-0.47

Чыганаклар

-0.47

 getItemCount

-0.46

autogui

-0.46

 garantire

-0.46

POSITIVE LOGITS

 disappointing

1.08

 disappoint

1.00

 disappointed

0.98

 overpriced

0.89

 disappointment

0.89

 underwhelming

0.87

 poorly

0.87

LookAnd

0.83

残念

0.82

 disappointments

0.80

Activations Density 0.162%

negative sentiments about stories or movies

Tokens preceding negative conjunctions

negative outcomes

No Comments

No Known Activations