INDEX

Explanations

opportunities or chances for something to happen

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

hemat

-0.82

aida

-0.73

unit

-0.68

eros

-0.64

ashion

-0.64

cott

-0.64

hematic

-0.63

aming

-0.63

sis

-0.62

arling

-0.62

POSITIVE LOGITS

 opportunity

1.08

 afforded

1.01

 opportunities

1.00

 Opportunity

0.91

llor

0.89

 Opportun

0.79

 presented

0.71

spective

0.71

izons

0.70

 lapse

0.68

Activations Density 0.651%

opportunities or chances for something to happen

No Comments

No Known Activations