INDEX

Explanations

references to groups or teams in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

+#+#

-1.01

 CreateTagHelper

-0.99

WriteBarrier

-0.98

 AppCompatTheme

-0.85

rhe

-0.85

 ComVisible

-0.82

DrawerToggle

-0.82

TagMode

-0.80

 мәкал

-0.79

 useRef

-0.78

POSITIVE LOGITS

 squad

0.98

 Squad

0.84

 squads

0.79

squad

0.75

 syndrome

0.69

 wellbeing

0.67

 Olsson

0.67

 molecules

0.64

 Wellbeing

0.63

Squad

0.61

Activations Density 0.084%

references to groups or teams in various contexts

No Comments

No Known Activations