INDEX

Explanations

phrases indicating significant impacts or effects on health and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

SequentialGroup

-0.75

 esqu

-0.55

,:),

-0.54

ChildScrollView

-0.53

 ComVisible

-0.53

Etymology

-0.53

={({

-0.53

 Survive

-0.52

내

-0.52

 CELEBR

-0.51

POSITIVE LOGITS

 impact

1.01

 effect

0.89

impact

0.83

effect

0.82

 affect

0.82

 EFFECT

0.80

 Impact

0.78

 effects

0.77

Impact

0.76

 impacto

0.75

Activations Density 0.324%

phrases indicating significant impacts or effects on health and well-being

No Comments

No Known Activations