INDEX

Explanations

medical terms and diagnoses

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

IBLE

-0.61

Recommend

-0.58

"!

-0.55

cause

-0.54

":"/

-0.53

again

-0.52

FORE

-0.52

 unrecogn

-0.52

 clot

-0.52

ISON

-0.51

POSITIVE LOGITS

Â®,

1.06

and

0.93

,[

0.88

(),

0.83

-,

0.83

0.81

*,

0.80

0.79

or

0.76

+,

0.73

Activations Density 0.670%

medical terms and diagnoses

No Comments

No Known Activations

medical terms and diagnoses

No Comments

No Known Activations