INDEX

Explanations

comparisons using the word "than"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alogy

-0.80

alf

-0.71

ieri

-0.69

idon

-0.67

cean

-0.65

atis

-0.65

ramid

-0.65

olis

-0.64

pillar

-0.63

xia

-0.63

POSITIVE LOGITS

 half

0.94

 halfway

0.81

 cents

0.78

 Â½

0.76

whelming

0.74

 stellar

0.72

 expected

0.69

osponsors

0.69

 dozen

0.68

expected

0.68

Activations Density 0.036%

comparisons using the word "than"

No Comments

No Known Activations