INDEX

Explanations

phrases that indicate participation or inclusion in various activities or contexts

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

"involved in" and its variations

np_acts-logits-general · gemini-2.0-flash

involvement or participation

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

ers

-0.61

-0.52

く

-0.50

 αυτό

-0.50

 pianta

-0.49

mares

-0.49

chtigkeit

-0.48

 tombe

-0.48

 retraite

-0.47

 alimentaires

-0.47

POSITIVE LOGITS

 Involved

1.05

 involve

1.05

 involved

1.04

involved

1.01

 Involvement

0.99

 INVOL

0.98

 involvement

0.97

 involves

0.89

rungsseite

0.88

 INVOLVED

0.87

Activations Density 0.085%

phrases that indicate participation or inclusion in various activities or contexts

"involved in" and its variations

involvement or participation

No Comments

No Known Activations