INDEX

Explanations

dates and locations

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

%%

-0.74

$$

-0.68

NOW

-0.67

tre

-0.65

 accounted

-0.65

CLASSIFIED

-0.64

soever

-0.64

 ingred

-0.62

 therein

-0.62

 importantly

-0.61

POSITIVE LOGITS

 conjunction

1.39

 lieu

1.35

 accordance

1.24

patient

1.16

 vitro

1.11

 spite

1.06

 order

1.03

ked

1.03

 favor

1.03

 relation

1.03

Activations Density 1.049%

dates and locations

No Comments

No Known Activations