INDEX

Explanations

occurrences of the word "to" in various contexts

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

"To" followed by specific characters

np_acts-logits-general · gemini-2.0-flash

to followed by OM or jiro or Primitive

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

oplayer

-0.78

phrine

-0.70

iastes

-0.69

InitVars

-0.69

stateProvider

-0.67

 pageContext

-0.63

Cordialement

-0.63

bamos

-0.63

XtraGrid

-0.61

 esternos

-0.60

POSITIVE LOGITS

to

0.97

TO

0.95

To

0.92

TO

0.90

To

0.87

eto

0.76

Ato

0.74

ato

0.70

toi

0.70

yto

0.68

Activations Density 0.180%

occurrences of the word "to" in various contexts

"To" followed by specific characters

to followed by OM or jiro or Primitive

No Comments

No Known Activations