INDEX

Explanations

instructions or steps in a process

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

 dstg

-0.55

':

-0.54

 Belfast

-0.54

DCS

-0.54

cigarettes

-0.54

Dear

-0.52

dor

-0.51

Joined

-0.50

Hey

-0.49

abetes

-0.49

POSITIVE LOGITS

 however

1.21

 therefore

1.04

 moreover

1.03

 meanwhile

0.92

 furthermore

0.92

anwhile

0.83

 additionally

0.80

 thus

0.73

 also

0.72

 though

0.71

Activations Density 10.961%

instructions or steps in a process

No Comments

No Known Activations