INDEX

Explanations

instances where the word "that" is followed by another word

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

aukee

-0.82

Guard

-0.73

oses

-0.69

andem

-0.68

rack

-0.66

zman

-0.65

arest

-0.64

backer

-0.63

gur

-0.62

POSITIVE LOGITS

 although

1.02

 they

0.93

 there

0.91

soever

0.89

 whoever

0.84

"[

0.79

we

0.77

 despite

0.75

 whereas

0.73

 whilst

0.73

Activations Density 1.502%

instances where the word "that" is followed by another word

No Comments

No Known Activations