INDEX

Explanations

words related to trust

oai_token-act-pair · gpt-3.5-turbo

discussions surrounding trust

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

pmwiki

-0.96

OPLE

-0.80

 Vide

-0.70

nesota

-0.69

neapolis

-0.69

gger

-0.68

Dispatch

-0.68

ozo

-0.68

apply

-0.67

ItemTracker

-0.66

POSITIVE LOGITS

worthiness

1.48

 trust

1.03

worthy

0.98

 trusts

0.92

ees

0.89

lessly

0.86

 trusting

0.85

fulness

0.79

fully

0.77

full

0.72

Activations Density 0.014%

words related to trust

discussions surrounding trust

No Known Activations