INDEX

Explanations

phrases related to putting together pieces of information or clues to form a coherent narrative or solution

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

 facult

-0.66

DragonMagazine

-0.62

ivity

-0.61

 Lauder

-0.57

usable

-0.56

OTOS

-0.55

 latitude

-0.54

inem

-0.53

Ĥİ

-0.53

POSITIVE LOGITS

ishly

1.07

 away

0.96

 havoc

0.94

efully

0.93

kered

0.92

 forth

0.89

out

0.84

addle

0.83

ulate

0.82

uled

0.82

Activations Density 1.699%

phrases related to putting together pieces of information or clues to form a coherent narrative or solution

No Comments

No Known Activations