INDEX

Explanations

words related to radar systems

oai_token-act-pair · gpt-3.5-turbo

instances and mentions of radar

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Kind

-0.78

atern

-0.73

anza

-0.72

TON

-0.71

bern

-0.70

È

-0.69

adra

-0.69

signed

-0.68

comes

-0.67

Ã§a

-0.67

POSITIVE LOGITS

 radar

1.16

sonian

0.89

wip

0.86

 detector

0.84

 detectors

0.84

 censor

0.83

ionics

0.83

 absor

0.82

 blaster

0.82

 transmitter

0.80

Activations Density 0.008%

words related to radar systems

instances and mentions of radar

No Comments

No Known Activations