INDEX

Explanations

common elements and similarities between different scenarios or instances in a text

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gal

-0.55

 bystand

-0.54

 Marshal

-0.53

 initiation

-0.51

inker

-0.51

Gau

-0.51

 Prel

-0.51

unin

-0.51

 Emergency

-0.51

prim

-0.49

POSITIVE LOGITS

same

0.99

nings

0.72

 applies

0.70

kefeller

0.68

natureconservancy

0.67

 twice

0.66

ietal

0.66

ait

0.64

igne

0.64

inson

0.63

Activations Density 0.484%

common elements and similarities between different scenarios or instances in a text

No Comments

No Known Activations