INDEX

Explanations

words related to software development methods and technologies

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

ufact

-0.64

uador

-0.63

ories

-0.61

mens

-0.58

 Nurs

-0.56

 Tray

-0.56

mare

-0.53

 Nationals

-0.53

 Tacoma

-0.53

 platoon

-0.53

POSITIVE LOGITS

0.95

ãĢĤ

0.88

;)

0.84

0.83

:)

0.82

.[

0.82

.,

0.79

:-)

0.78

Activations Density 1.843%

words related to software development methods and technologies

No Comments

No Known Activations