INDEX

Explanations

phrases related to dissociation and traumatic experiences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glers

-0.79

 Werewolf

-0.72

 Archdemon

-0.72

çĦ

-0.68

 stakes

-0.66

 Goff

-0.65

FORE

-0.64

 Kinnikuman

-0.63

 Roose

-0.61

================

-0.61

POSITIVE LOGITS

imilar

1.43

ociation

1.41

ipation

1.41

oci

1.36

ident

1.31

olving

1.30

ociated

1.29

ension

1.22

ertation

1.20

ociate

1.17

Activations Density 0.012%

phrases related to dissociation and traumatic experiences

No Comments

No Known Activations