INDEX

Explanations

the word "so" in various contexts and frequencies

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

Following "so"

np_acts-logits-general · gemini-2.0-flash

so

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelf

-0.61

 Cæsar

-0.60

ſelves

-0.58

 Diony

-0.57

 snippetHide

-0.56

 entanto

-0.54

 mandal

-0.52

MDC

-0.52

EFE

-0.52

 כך

-0.52

POSITIVE LOGITS

it

1.17

 there

1.02

we

1.01

 they

0.93

0.85

 naturally

0.78

no

0.78

 maybe

0.74

why

0.72

 perhaps

0.72

Activations Density 0.071%

the word "so" in various contexts and frequencies

Following "so"

so

No Comments

No Known Activations