INDEX

Explanations

words related to visibility or presence

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

"appear" or its variations

np_acts-logits-general · gemini-2.0-flash

appear to be

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.51

?></

-0.51

 Total

-0.50

vid

-0.50

sky

-0.47

 Base

-0.47

kreises

-0.47

tragung

-0.47

言うと

-0.46

TOTAL

-0.46

POSITIVE LOGITS

 appearances

1.10

 Appearances

1.09

 Appear

1.02

Appearances

0.99

 Appears

0.97

 appear

0.96

 appearance

0.95

 APPE

0.95

 Appearance

0.91

appear

0.90

Activations Density 0.160%

words related to visibility or presence

"appear" or its variations

appear to be

No Comments

No Known Activations