INDEX

Explanations

phrases related to political and legal issues

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

"]=>

-0.65

 Latter

-0.63

.--

-0.60

 Became

-0.58

orn

-0.57

LOG

-0.57

 Clicker

-0.56

lus

-0.56

lord

-0.54

.—

-0.52

POSITIVE LOGITS

 albeit

0.95

 preferably

0.81

particularly

0.81

 namely

0.81

aka

0.79

including

0.75

albeit

0.73

 including

0.71

emort

0.70

 comprising

0.69

Activations Density 0.294%

phrases related to political and legal issues

No Comments

No Known Activations