INDEX

Explanations

phrases related to comparisons or contrasts between different entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

upon

-0.80

ocate

-0.69

ritch

-0.68

atron

-0.65

ties

-0.64

ibur

-0.63

lessly

-0.61

Ì¶

-0.61

aurus

-0.60

lance

-0.60

POSITIVE LOGITS

 occasions

1.51

 basis

1.40

 occasion

1.37

 behalf

1.33

 doorstep

1.26

 grounds

1.18

 verge

1.15

eve

1.15

 sidelines

1.14

 heels

1.10

Activations Density 1.730%

phrases related to comparisons or contrasts between different entities

No Comments

No Known Activations