INDEX

Explanations

words related to deception or trickery

oai_token-act-pair · gpt-3.5-turbo

words or phrases related to 'con' prefixes and concepts associated with conformity and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

TPS

-0.68

 Norn

-0.64

assetsadobe

-0.63

 gelatin

-0.62

 Acid

-0.60

ACK

-0.60

 Grove

-0.59

terday

-0.59

 footprints

-0.58

 calves

-0.58

POSITIVE LOGITS

clusively

1.26

gru

1.21

clave

1.20

joined

1.18

undrum

1.16

gres

1.16

versely

1.10

clus

1.10

notation

1.08

naissance

1.06

Activations Density 0.013%

words related to deception or trickery

words or phrases related to 'con' prefixes and concepts associated with conformity and its implications

No Comments

No Known Activations