INDEX

Explanations

phrases related to comparisons and classifications involving groups or categories

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

preceding "directions", "hospitals", or found after "both"

np_acts-logits-general · gemini-2.0-flash

both X and Y

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 ovunque

-0.57

 spéciaux

-0.56

 altrimenti

-0.55

 banyak

-0.54

 zelfs

-0.53

 sonst

-0.53

 Banyak

-0.51

 adicionales

-0.51

 alcun

-0.51

 supplémentaires

-0.50

POSITIVE LOGITS

 single

0.92

 general

0.88

 regular

0.86

 Regular

0.85

 Standard

0.82

 residential

0.82

 Single

0.81

 basic

0.79

 Ordinary

0.79

 heterosexual

0.79

Activations Density 1.163%

phrases related to comparisons and classifications involving groups or categories

preceding "directions", "hospitals", or found after "both"

both X and Y

No Comments

No Known Activations