INDEX

Explanations

words related to devaluing or diminishing in value

oai_token-act-pair · gpt-3.5-turbo

terms related to valuation and dishonesty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Agency

-0.73

 Helmet

-0.73

 Directions

-0.70

 Andromeda

-0.69

WORK

-0.69

 Contra

-0.69

 Sight

-0.69

Stars

-0.69

 Rider

-0.68

 Wings

-0.68

POSITIVE LOGITS

 deval

1.60

ued

1.31

uing

1.28

uation

1.23

ues

1.12

uations

1.06

ftime

0.99

xual

0.97

uted

0.89

uable

0.89

Activations Density 0.018%

words related to devaluing or diminishing in value

terms related to valuation and dishonesty

No Comments

No Known Activations