INDEX

Explanations

comparisons and similarities in situations

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

"Similar" or "same" followed by a noun

np_acts-logits-general · gemini-2.0-flash

similar situations or happenings

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

 pinulongan

-0.68

Hentet

-0.54

Zunanje

-0.53

:✨

-0.52

culata

-0.52

 uffic

-0.51

AutoField

-0.51

 Numerade

-0.50

 препратки

-0.50

Specific

-0.49

POSITIVE LOGITS

 situation

0.79

situation

0.66

 Situation

0.64

 SITUATION

0.63

Situation

0.63

 approach

0.61

approach

0.58

 BoxFit

0.57

 APPROACH

0.56

 situación

0.55

Activations Density 0.345%

comparisons and similarities in situations

"Similar" or "same" followed by a noun

similar situations or happenings

No Comments

No Known Activations