INDEX

Explanations

scientific and research-related terms and information

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

 guiActiveUnfocused

-0.78

retty

-0.69

ierrez

-0.64

enta

-0.64

blogspot

-0.62

itures

-0.62

enza

-0.61

rays

-0.60

 PHOTO

-0.59

rament

-0.59

POSITIVE LOGITS

çīĪ

0.80

×¨

0.66

çİĭ

0.63

é¾į

0.61

åĽ

0.61

\\\\\\\\\\\\\\\\

0.60

×

0.59

×Ļ×

0.58

×Ļ

0.57

×ĳ

0.57

Activations Density 0.049%

scientific and research-related terms and information

No Comments

No Known Activations