INDEX

Explanations

phrases related to starting or beginning something

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

lua

-0.70

hof

-0.66

jong

-0.64

come

-0.63

arily

-0.60

jah

-0.59

ificent

-0.58

velop

-0.58

mo

-0.57

Ga

-0.56

POSITIVE LOGITS

 residence

1.06

rights

0.89

 positions

0.73

 position

0.72

 arms

0.70

 sugg

0.68

 stances

0.66

ibilities

0.65

IPM

0.64

stantial

0.64

Activations Density 0.023%

phrases related to starting or beginning something

No Comments

No Known Activations