INDEX

Explanations

words related to medical conditions, treatments, and procedures that may involve potential risk or harm

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

 McGee

-0.66

Ô

-0.63

bye

-0.61

 Skinner

-0.59

Browser

-0.58

 Journalists

-0.58

 Kimber

-0.57

 McCabe

-0.56

Ri

-0.55

Fri

-0.55

POSITIVE LOGITS

rophic

1.16

rophe

0.92

anship

0.85

roph

0.81

asis

0.80

atic

0.79

otypes

0.78

ucle

0.77

oration

0.77

istics

0.77

Activations Density 0.049%

words related to medical conditions, treatments, and procedures that may involve potential risk or harm

No Comments

No Known Activations