INDEX

Explanations

phrases related to agreements or treaties

oai_token-act-pair · gpt-3.5-turbo

instances of the word "accord" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

################

-0.80

GER

-0.76

APD

-0.72

################################

-0.68

CHO

-0.63

çīĪ

-0.62

 bottleneck

-0.62

Ku

-0.62

AMA

-0.61

lycer

-0.60

POSITIVE LOGITS

ion

1.07

ords

1.02

ioned

0.92

romeda

0.90

 accord

0.86

ions

0.85

ivalent

0.84

inet

0.83

ian

0.78

ements

0.78

Activations Density 0.016%

phrases related to agreements or treaties

instances of the word "accord" and its variations

No Comments

No Known Activations