INDEX

Explanations

phrases related to legal and judicial processes

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

 testament

-0.77

 reborn

-0.73

 transformed

-0.71

¾

-0.69

 recip

-0.66

 appre

-0.65

 disapp

-0.65

hens

-0.64

Äį

-0.62

¥

-0.61

POSITIVE LOGITS

inventoryQuantity

0.86

 harms

0.79

Ïī

0.78

Spoiler

0.76

sites

0.71

ãĤ¨ãĥ«

0.71

 Sundays

0.70

nit

0.69

enged

0.69

natureconservancy

0.68

Activations Density 0.063%

phrases related to legal and judicial processes

No Comments

No Known Activations