INDEX

Explanations

terms related to surveillance or tracking activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "monitoring."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Anth

-0.82

onian

-0.81

win

-0.73

sis

-0.73

dx

-0.71

dy

-0.70

clus

-0.70

bp

-0.68

ONT

-0.68

bite

-0.67

POSITIVE LOGITS

 monitoring

1.28

 monitored

1.16

 monitors

1.10

 monitor

1.00

itored

0.89

 Monitoring

0.85

 tracks

0.83

 Monitor

0.82

 attent

0.81

ank

0.80

Activations Density 0.011%

terms related to surveillance or tracking activities

instances of the word "monitoring."

No Comments

No Known Activations