INDEX

Explanations

phrases related to descriptions of events happening alongside something else

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

asse

-0.79

jab

-0.79

Ì¶

-0.72

ortex

-0.72

oria

-0.71

ck

-0.69

nexus

-0.69

ggle

-0.68

bell

-0.67

ahime

-0.67

POSITIVE LOGITS

 others

0.78

 fellow

0.74

 hers

0.73

lihood

0.72

him

0.69

 other

0.68

 ours

0.68

 yours

0.66

 colleagues

0.66

pins

0.65

Activations Density 0.041%

phrases related to descriptions of events happening alongside something else

No Comments

No Known Activations