INDEX

Explanations

references to a person's reputation or credibility

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

Follows "well" or "-" and means "known" or "suited"

np_acts-logits-general · gemini-2.0-flash

well known qualities

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

WebVitals

-0.64

 aveug

-0.62

IUrlHelper

-0.59

 ſeveral

-0.59

 незавершена

-0.59

zarchiwizowane

-0.58

cocci

-0.58

 fometimes

-0.58

 élégante

-0.58

esModule

-0.58

POSITIVE LOGITS

 known

0.74

known

0.66

 liked

0.64

 behaved

0.64

 suited

0.63

 versed

0.62

nigh

0.62

 respected

0.59

 grounded

0.59

 founded

0.58

Activations Density 0.100%

references to a person's reputation or credibility

Follows "well" or "-" and means "known" or "suited"

well known qualities

No Comments

No Known Activations