INDEX

Explanations

words related to medical and pharmaceutical topics

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

UTERS

-0.83

endment

-0.74

 Sasha

-0.70

ouston

-0.69

ĪĴ

-0.68

isconsin

-0.68

ongyang

-0.66

ĵĺ

-0.66

orney

-0.65

mercial

-0.64

POSITIVE LOGITS

oids

0.96

ious

0.91

oid

0.90

holm

0.87

iously

0.86

ding

0.82

ded

0.82

geist

0.81

bucks

0.77

odon

0.75

Activations Density 0.038%

words related to medical and pharmaceutical topics

No Comments

No Known Activations