INDEX

Explanations

the phrase "as soon as."

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

ricks

-0.79

roo

-0.71

uph

-0.67

âĹ¼

-0.67

sson

-0.64

bold

-0.63

arnaev

-0.63

ARS

-0.62

tie

-0.62

tw

-0.62

POSITIVE LOGITS

 practicable

0.95

 possible

0.87

 they

0.78

 clicked

0.76

 payday

0.75

 dawn

0.73

 whiff

0.70

 someone

0.70

 somebody

0.69

 sunrise

0.69

Activations Density 0.019%

the phrase "as soon as."

No Comments

No Known Activations