INDEX

Explanations

phrases related to privacy and personal data management

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

Tokens often followed by numbers or symbols

np_acts-logits-general · gemini-2.0-flash

government payment

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

 ſtate

-1.17

 pleaſure

-1.13

 ſever

-1.10

 ſta

-1.09

 myſelf

-1.09

 purpoſe

-1.08

 ſche

-1.06

 houſe

-1.06

 itſelf

-1.02

 raiſ

-1.00

POSITIVE LOGITS

0.64

er

0.62

0.60

0.58

mit

0.56

0.55

ab

0.55

Activations Density 0.025%

phrases related to privacy and personal data management

Tokens often followed by numbers or symbols

government payment

No Comments

No Known Activations