INDEX

Explanations

sentences that provide explanations or reasons for a given situation or action

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

nces

-0.70

 torch

-0.70

readable

-0.69

kun

-0.68

imet

-0.65

uania

-0.65

borg

-0.64

ona

-0.63

adiq

-0.63

istered

-0.62

POSITIVE LOGITS

Because

1.22

Reason

1.20

 Because

1.19

 reasons

1.13

Cause

1.13

cause

1.11

 Reasons

1.11

ecause

1.07

WHY

1.00

 because

0.97

Activations Density 0.169%

sentences that provide explanations or reasons for a given situation or action

No Comments

No Known Activations