INDEX

Explanations

phrases related to determination and commitment

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

jri

-0.69

stellar

-0.67

itive

-0.66

amaz

-0.64

 Kinn

-0.64

assic

-0.62

York

-0.61

 Stern

-0.61

 Atkinson

-0.61

 Globe

-0.61

POSITIVE LOGITS

 ought

1.06

'll

1.04

 should

0.99

'd

0.96

're

0.95

 shouldn

0.92

 SHOULD

0.92

 could

0.92

 might

0.90

 cannot

0.89

Activations Density 0.265%

phrases related to determination and commitment

No Comments

No Known Activations