INDEX

Explanations

phrases describing comparisons between different entities

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

istries

-0.67

urai

-0.63

wrong

-0.63

atis

-0.61

incial

-0.61

 pronounce

-0.58

aukee

-0.57

ims

-0.56

 shuffle

-0.56

 reperto

-0.56

POSITIVE LOGITS

 oneself

0.86

 ordinary

0.82

stood

0.73

 course

0.73

the

0.70

 actual

0.69

any

0.68

 neighboring

0.68

 lowly

0.66

 others

0.64

Activations Density 0.037%

phrases describing comparisons between different entities

No Comments

No Known Activations