INDEX

Explanations

numerical values that appear to be quantities or measurements

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

swick

-0.79

lycer

-0.71

xual

-0.70

ophon

-0.68

worldly

-0.68

cles

-0.65

sed

-0.64

urger

-0.64

quit

-0.62

ppo

-0.62

POSITIVE LOGITS

Thirty

1.21

 ILCS

0.98

0.76

 gallon

0.74

th

0.71

iam

0.71

anging

0.71

ushima

0.70

âĺħ

0.69

%-

0.69

Activations Density 0.808%

numerical values that appear to be quantities or measurements

No Comments

No Known Activations