INDEX

Explanations

descriptive physical attributes of characters

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

appearance and observations

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 démocr

-0.62

intios

-0.56

 utvik

-0.55

 devenus

-0.53

 förr

-0.52

뀐

-0.52

rrggbb

-0.52

ActionMode

-0.50

 spéciaux

-0.50

 felhasznál

-0.49

POSITIVE LOGITS

 obviously

0.65

 obvious

0.65

 visibly

0.65

 seemed

0.64

 apparent

0.63

 wearing

0.61

 seeming

0.60

 tattoos

0.59

obviously

0.57

ISupport

0.56

Activations Density 0.176%

descriptive physical attributes of characters

appearance and observations

No Comments

No Known Activations