INDEX

Explanations

numerical values, particularly in the context of ratings or rankings

oai_token-act-pair · gpt-4o-mini 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

lier

-0.71

yond

-0.68

antic

-0.66

oglu

-0.64

leases

-0.63

leasing

-0.63

nu

-0.63

ledged

-0.62

anu

-0.61

lington

-0.60

POSITIVE LOGITS

 Photos

0.79

 Expand

0.74

 certs

0.74

 Â·

0.69

 msec

0.68

 Advertisement

0.64

 è£ıè

0.63

 Alphabet

0.63

 Seller

0.60

=-=-=-=-

0.59

Activations Density 0.042%

numerical values, particularly in the context of ratings or rankings

No Comments

No Known Activations