INDEX

Explanations

terms and phrases related to trust and trustworthiness

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

"trust"

np_acts-logits-general · gemini-2.0-flash

trust and trustworthiness

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

ⓧ

-0.68

IUrlHelper

-0.60

abetes

-0.60

ANNES

-0.60

enumi

-0.59

 ITIS

-0.59

exprimer

-0.59

醐

-0.58

 vela

-0.58

bry

-0.58

POSITIVE LOGITS

 trust

1.44

Trust

1.43

 trusts

1.35

 Trust

1.32

trust

1.31

 TRUST

1.29

 trusting

1.26

TRUST

1.25

 trusted

1.20

 trustworthy

1.07

Activations Density 0.106%

terms and phrases related to trust and trustworthiness

"trust"

trust and trustworthiness

No Comments

No Known Activations