INDEX

Explanations

instances of the word "Both" followed by a comparison or contrast between two entities or concepts

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

xus

-0.77

ugu

-0.77

nect

-0.75

renheit

-0.75

uably

-0.74

ilit

-0.71

uable

-0.70

 nowhere

-0.68

biz

-0.68

vich

-0.68

POSITIVE LOGITS

 sexes

1.68

 sides

1.57

 halves

1.37

 genders

1.36

 parties

1.09

 coasts

0.92

 extremes

0.91

 Houses

0.90

 ends

0.86

 directions

0.81

Activations Density 0.360%

instances of the word "Both" followed by a comparison or contrast between two entities or concepts

No Comments

No Known Activations