INDEX

Explanations

terms related to trustworthiness and reliability

oai_token-act-pair · gpt-3.5-turbo

terminology related to reliability and dependability issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ri

-0.68

ynthesis

-0.68

rhy

-0.64

CTR

-0.64

NCT

-0.62

 traffickers

-0.60

ibraries

-0.60

 promul

-0.59

 Banks

-0.59

 Torrent

-0.59

POSITIVE LOGITS

able

1.72

ably

1.63

ables

1.46

ABLE

1.39

ingly

1.38

worthy

1.34

vable

1.30

ledged

1.28

ability

1.22

ivable

1.21

Activations Density 0.084%

terms related to trustworthiness and reliability

terminology related to reliability and dependability issues

No Comments

No Known Activations