INDEX

Explanations

phrases indicating simplicity or ease of understanding

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

hips

-0.78

eters

-0.78

reon

-0.75

grave

-0.74

raints

-0.72

mbuds

-0.68

orp

-0.66

orf

-0.64

arians

-0.63

emp

-0.62

POSITIVE LOGITS

Jet

0.93

going

0.91

 prey

0.80

wallet

0.80

coded

0.78

 easy

0.72

accessible

0.70

 forgiving

0.70

 minded

0.70

ily

0.69

Activations Density 0.024%

phrases indicating simplicity or ease of understanding

No Comments

No Known Activations