INDEX

Explanations

words related to military actions and warfare, particularly focusing on air strikes

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Negative Logits

 Mori

-0.70

 Millenn

-0.68

Cla

-0.67

 Principles

-0.66

 Howell

-0.65

 Hots

-0.64

 Avery

-0.63

 Welsh

-0.63

 Motorsport

-0.63

Ys

-0.61

POSITIVE LOGITS

waves

1.35

planes

1.22

plane

1.21

raid

1.21

ship

1.19

ships

1.17

tight

1.14

lift

1.13

condition

1.05

liners

1.05

Activations Density 0.022%

words related to military actions and warfare, particularly focusing on air strikes

No Known Activations