INDEX

Explanations

phrases related to self-reference or self-awareness

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

following "self-" prefix

np_acts-logits-general · gemini-2.0-flash

self-hyphenated descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

YOND

-0.70

VideoCapture

-0.62

 PLWABN

-0.57

Weblinks

-0.55

kör

-0.54

 Recipro

-0.52

 parteci

-0.51

strokeStyle

-0.51

 peccato

-0.50

 utafitiHapana

-0.50

POSITIVE LOGITS

 nahilalakip

0.76

 flag

0.56

flag

0.55

 Flag

0.52

tadır

0.50

centered

0.49

 importance

0.49

righ

0.49

 wichtiger

0.48

 important

0.48

Activations Density 0.153%

phrases related to self-reference or self-awareness

following "self-" prefix

self-hyphenated descriptors

No Comments

No Known Activations