INDEX

Explanations

questions related to legal or political matters

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 background

-0.69

 marsh

-0.68

ality

-0.65

aper

-0.64

 evening

-0.63

dex

-0.63

 colon

-0.63

arm

-0.62

 foreground

-0.62

 swamp

-0.62

POSITIVE LOGITS

 Nope

1.39

 Probably

1.30

 Answer

1.30

 Surely

1.30

 Well

1.29

 Certainly

1.24

Answer

1.20

 Wouldn

1.19

 Possibly

1.18

Why

1.18

Activations Density 0.906%

questions related to legal or political matters

No Comments

No Known Activations