INDEX

Explanations

phrases related to comparisons or distinctions 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_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

oldemort

-0.66

ario

-0.64

irez

-0.63

ysc

-0.63

idation

-0.62

nery

-0.62

ober

-0.61

ossession

-0.61

adal

-0.61

ipation

-0.61

POSITIVE LOGITS

st

0.91

Īè

0.86

Ĳ

0.85

Ĭ±

0.84

ĪĴ

0.83

 those

0.82

stad

0.77

 peers

0.75

ī

0.75

 them

0.72

Activations Density 0.414%

phrases related to comparisons or distinctions between different entities

No Comments

No Known Activations