INDEX

Explanations

proper nouns, specifically names of people

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "presume" 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

 Lions

-0.73

 Abyssal

-0.70

 Salvation

-0.65

 brackets

-0.64

 subt

-0.64

STAR

-0.62

ISM

-0.62

 dots

-0.62

ļéĨĴ

-0.61

 Italians

-0.61

POSITIVE LOGITS

cription

1.20

chool

1.19

byter

1.14

ervation

1.14

erves

1.10

ervative

1.09

umed

1.08

idency

1.07

erving

1.07

ervatives

1.06

Activations Density 0.017%

proper nouns, specifically names of people

mentions of the word "presume" and its variations

No Comments

No Known Activations