INDEX

Explanations

words related to medical therapies and treatments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

ruary

-0.77

 hither

-0.74

 Archdemon

-0.70

 Canal

-0.69

 Barron

-0.66

 innocence

-0.63

cember

-0.62

 goodbye

-0.61

uay

-0.60

 acknowled

-0.60

POSITIVE LOGITS

utic

0.89

utics

0.88

versible

0.84

 Devices

0.84

utical

0.81

ognitive

0.79

uclear

0.78

rex

0.78

ically

0.78

ensitive

0.77

Activations Density 0.009%

words related to medical therapies and treatments

No Comments

No Known Activations