INDEX

Explanations

references to future plans or intentions in research or writing contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 myſelf

-0.69

 itſelf

-0.63

 Paglinawan

-0.61

 themſelves

-0.61

\]

-0.61

Composable

-0.59

Eſ

-0.59

 himſelf

-0.59

BoxShadow

-0.57

 ainfi

-0.57

POSITIVE LOGITS

 next

0.84

contentLoaded

0.70

Next

0.62

next

0.62

 Next

0.58

次回は

0.55

 NEXT

0.55

 näch

0.54

 cherchés

0.54

 próxima

0.53

Activations Density 0.307%

references to future plans or intentions in research or writing contexts

No Comments

No Known Activations