INDEX

Explanations

references to the name "Jon."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.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

holders

-0.77

doors

-0.65

ledged

-0.64

sided

-0.63

MEN

-0.62

 IMAGES

-0.62

 nuns

-0.61

 salts

-0.60

 cannabinoids

-0.60

ATURE

-0.59

POSITIVE LOGITS

athon

1.26

nie

1.12

ny

1.12

Ben

1.02

athan

0.99

atan

0.98

Ã¡s

0.94

onymous

0.91

sey

0.90

uments

0.89

Activations Density 0.004%

references to the name "Jon."

No Comments

No Known Activations