INDEX

Explanations

positive outcomes and expressions of satisfaction

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

uca

-0.79

interstitial

-0.73

inian

-0.71

roots

-0.69

raid

-0.67

agus

-0.66

UME

-0.66

mber

-0.64

ricanes

-0.64

ockey

-0.63

POSITIVE LOGITS

Excellent

1.01

 improved

0.97

 improves

0.97

 congr

0.95

albeit

0.95

 inexpensive

0.95

 satisfactory

0.91

 prosper

0.89

Awesome

0.88

 improving

0.88

Activations Density 3.465%

positive outcomes and expressions of satisfaction

No Comments

No Known Activations