INDEX

Explanations

references to the letter 'T' in various contexts

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

"T" followed by a lowercase letter

np_acts-logits-general · gemini-2.0-flash

words starting with T

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

om

-0.64

ag

-0.51

han

-0.50

 merci

-0.50

 moks

-0.49

or

-0.47

hou

-0.47

hall

-0.46

OURS

-0.46

POSITIVE LOGITS

parsedMessage

0.72

Personensuche

0.71

 صوتيه

0.65

RetentionPolicy

0.65

 nakalista

0.64

ThroughAttribute

0.63

findpost

0.62

imageshack

0.61

trường

0.61

 initComponents

0.61

Activations Density 0.216%

references to the letter 'T' in various contexts

"T" followed by a lowercase letter

words starting with T

No Comments

No Known Activations