INDEX

Explanations

mentions of companies, organizations, or specific services and issues related to them

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

holes

-0.79

hari

-0.78

lehem

-0.76

beck

-0.73

":[

-0.72

umber

-0.72

umenthal

-0.71

Texture

-0.71

conom

-0.70

idences

-0.70

POSITIVE LOGITS

own

1.68

 flagship

1.27

 newest

1.16

 predecessor

1.09

 foray

1.06

 proprietary

1.03

 latest

1.02

 stance

0.96

 namesake

0.95

 approach

0.95

Activations Density 0.990%

mentions of companies, organizations, or specific services and issues related to them

No Comments

No Known Activations