INDEX

Explanations

phrases related to a time duration or period

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

zsche

-0.69

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.68

tle

-0.64

reme

-0.62

redict

-0.62

atem

-0.62

Case

-0.60

owler

-0.59

ower

-0.59

ãĥĨãĤ£

-0.59

POSITIVE LOGITS

 captivity

0.80

 abroad

0.72

 touring

0.68

 composing

0.67

boarding

0.67

packing

0.67

ONY

0.67

 overseas

0.67

 operating

0.67

Reviewer

0.67

Activations Density 0.464%

phrases related to a time duration or period

No Comments

No Known Activations