INDEX

Explanations

references to medications and medical 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

*/(

-0.72

 innocence

-0.68

footed

-0.67

 Mavericks

-0.65

 borough

-0.64

 Hornets

-0.64

xual

-0.61

 Carnival

-0.61

 tease

-0.61

 swirl

-0.60

POSITIVE LOGITS

inally

1.22

inals

1.07

aceutical

1.05

inal

1.04

aid

0.99

arie

0.94

iate

0.93

are

0.93

onom

0.92

aret

0.91

Activations Density 0.009%

references to medications and medical treatments

No Comments

No Known Activations