INDEX

Explanations

references to the word 'wo' and its variations in different contexts

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

Tokens starting with "Wo" or "wo"

np_acts-logits-general · gemini-2.0-flash

words starting with wo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-0.78

Попис

-0.70

 preſent

-0.67

 myſelf

-0.67

 himſelf

-0.67

 nakalista

-0.67

 themſelves

-0.65

 Cæsar

-0.64

 pleaſure

-0.64

 Monfieur

-0.63

POSITIVE LOGITS

Wo

0.77

wo

0.72

__*/

0.64

Wo

0.62

 Wohl

0.60

Voodoo

0.53

WO

0.53

\{\\

0.51

Woj

0.51

Wor

0.50

Activations Density 0.081%

references to the word 'wo' and its variations in different contexts

Tokens starting with "Wo" or "wo"

words starting with wo

No Comments

No Known Activations