INDEX

Explanations

the word "truck."

oai_token-act-pair · gpt-3.5-turbo

references to trucks and related vehicles

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

nces

-0.83

é»Ĵ

-0.76

 Seym

-0.72

ASED

-0.68

tle

-0.68

âĸ¬âĸ¬

-0.67

arial

-0.67

ternity

-0.65

 solder

-0.65

âĸ¬

-0.63

POSITIVE LOGITS

loads

1.37

load

1.23

 truck

1.03

yard

1.01

 trucks

0.99

 tractor

0.93

erness

0.89

driver

0.83

wagon

0.82

 convoy

0.81

Activations Density 0.024%

the word "truck."

references to trucks and related vehicles

No Comments

No Known Activations