INDEX

Explanations

personal pronouns referring to people and organizations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sussex

-0.61

 Conquest

-0.59

 Colonial

-0.59

 Vers

-0.59

 Plaint

-0.58

 Dome

-0.55

icle

-0.55

fill

-0.55

 apex

-0.54

 Quarterly

-0.54

POSITIVE LOGITS

 regretted

1.13

 encount

0.97

 intend

0.96

'd

0.95

 intends

0.93

 wished

0.92

 regrets

0.90

 intention

0.88

 personally

0.88

©¶æ

0.82

Activations Density 1.092%

personal pronouns referring to people and organizations

No Comments

No Known Activations