INDEX

Explanations

elements related to personal identity and social roles

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

preceding "had"

np_acts-logits-general · gemini-2.0-flash

single individuals or roles

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

Rhestr

-0.70

paravant

-0.68

oredCriteria

-0.66

]").

-0.64

ValueStyle

-0.63

 ganzen

-0.63

 تضيفلها

-0.62

astify

-0.61

 Various

-0.61

BeginContext

-0.61

POSITIVE LOGITS

Portale

0.60

 someone

0.59

 apiece

0.58

 jeden

0.57

 Jeden

0.52

 each

0.51

ésultat

0.51

Someone

0.50

Jeden

0.50

 somebody

0.48

Activations Density 0.868%

elements related to personal identity and social roles

preceding "had"

single individuals or roles

No Comments

No Known Activations