INDEX

Explanations

words related to physical shock or trauma

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

Not in Any Lists

No Comments

Negative Logits

 numbered

-0.79

 Ajax

-0.73

 Reach

-0.69

 Leilan

-0.67

 dating

-0.64

NEO

-0.63

 Juven

-0.61

 Homo

-0.61

 Cellular

-0.61

 Leth

-0.60

POSITIVE LOGITS

ifts

1.26

ifting

1.23

aded

1.23

ooting

1.22

apes

1.20

attering

1.19

adows

1.19

aders

1.18

apeshifter

1.16

ackle

1.16

Activations Density 0.016%

words related to physical shock or trauma

No Comments

No Known Activations