INDEX

Explanations

words and phrases related to trust and trustworthiness

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

"trust" or its variations

np_acts-logits-general · gemini-2.0-flash

trust and related notions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IUrlHelper

-0.68

ANNES

-0.63

ⓧ

-0.61

abetes

-0.58

laterra

-0.58

 Lordships

-0.58

 primas

-0.58

 AssemblyProduct

-0.57

persistent

-0.57

 ángeles

-0.55

POSITIVE LOGITS

Trust

1.03

 trusts

0.98

 Trust

0.96

TRUST

0.93

 trust

0.92

trust

0.92

 TRUST

0.91

 Trusts

0.79

worthiness

0.75

 trusting

0.71

Activations Density 0.081%

words and phrases related to trust and trustworthiness

"trust" or its variations

trust and related notions

No Comments

No Known Activations