INDEX

Explanations

actions involving looking, seeing, or observing

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

looking or direction

np_acts-logits-general · gemini-2.0-flash

looking in directions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Orrell

-0.65

WriteBarrier

-0.63

transQ

-0.61

Datuak

-0.60

 Appellee

-0.59

 AudioClip

-0.58

 Akismet

-0.58

 Orville

-0.57

ustimmung

-0.57

poleon

-0.57

POSITIVE LOGITS

 tajam

0.49

#+#

0.45

räder

0.45

новништво

0.45

WebServlet

0.45

了一眼

0.44

quam

0.44

 towards

0.43

bet

0.43

 към

0.43

Activations Density 0.073%

actions involving looking, seeing, or observing

looking or direction

looking in directions

No Comments

No Known Activations