INDEX

Explanations

names of people or 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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

ANA

-0.58

estyles

-0.58

çĶ°

-0.57

iable

-0.57

ixt

-0.57

acci

-0.56

ãĥĩãĤ£

-0.56

rio

-0.56

 Millennials

-0.55

Austin

-0.55

POSITIVE LOGITS

huh

0.59

)=(

0.58

âķĲ

0.56

 cleared

0.55

????????

0.55

 stret

0.54

[/

0.54

Lau

0.53

 handle

0.53

 tong

0.52

Activations Density 0.771%

names of people or locations

No Comments

No Known Activations