INDEX

Explanations

references to trust and trustworthiness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Anaconda

-0.94

Рабо

-0.82

 Scenes

-0.81

internalType

-0.80

 volks

-0.80

EDS

-0.79

avatars

-0.79

 Notepad

-0.79

 AppBundle

-0.79

neko

-0.79

POSITIVE LOGITS

 trust

2.83

 Trust

2.78

Trust

2.70

trust

2.66

 TRUST

2.53

TRUST

2.49

 trusts

2.49

 Trusts

2.14

 trusting

2.02

 trusted

1.85

Activations Density 0.047%

references to trust and trustworthiness

No Comments

No Known Activations