INDEX

Explanations

the word "trust" in various contexts

oai_token-act-pair · gpt-3.5-turbo

expressions related to trust

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pmwiki

-0.86

ploy

-0.81

nesota

-0.76

ffield

-0.76

zz

-0.75

ankind

-0.71

atre

-0.70

mort

-0.68

vention

-0.68

ventions

-0.67

POSITIVE LOGITS

worthiness

1.60

worthy

0.98

lessly

0.91

 trusting

0.90

 trust

0.86

iliate

0.78

 trustworthy

0.75

rals

0.72

 trusted

0.72

 confid

0.72

Activations Density 0.026%

the word "trust" in various contexts

expressions related to trust

No Comments

No Known Activations