INDEX

Explanations

expressions indicating excessive qualities or attributes

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

aarrggbb

-0.70

setVerticalGroup

-0.68

 snippetHide

-0.67

 AttributeSet

-0.65

+#+

-0.65

InjectAttribute

-0.62

Geplaatst

-0.62

InitVars

-0.62

WebVitals

-0.61

})));

-0.61

POSITIVE LOGITS

Too

1.20

Too

1.13

too

1.06

TOO

0.98

too

0.97

TOO

0.86

 zbyt

0.79

 enough

0.75

 demasi

0.71

 слишком

0.70

Activations Density 0.097%

expressions indicating excessive qualities or attributes

No Comments

No Known Activations