INDEX

Explanations

words related to advancements or improvements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pper

-0.67

 Peninsula

-0.66

agine

-0.66

ENA

-0.63

 vivid

-0.63

coh

-0.61

 snap

-0.60

olicited

-0.58

clad

-0.58

 combust

-0.58

POSITIVE LOGITS

ivism

1.49

iveness

1.28

ions

1.22

ives

1.18

ivity

1.17

ivist

1.10

ively

1.03

ional

0.99

 toward

0.96

 towards

0.95

Activations Density 0.021%

words related to advancements or improvements

No Comments

No Known Activations