INDEX

Explanations

references to legal or government documents and procedures

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

 Palest

-0.84

çīĪ

-0.69

RAD

-0.69

Interstitial

-0.64

Buyable

-0.63

 Izan

-0.61

 mainland

-0.60

 Circus

-0.60

æĪ¦

-0.59

ãĤ¬

-0.59

POSITIVE LOGITS

£

1.06

¿

1.02

º

0.98

Ń

0.94

Ĭ

0.93

¼

0.93

¬

0.93

¹

0.92

ı

0.91

Ķ

0.91

Activations Density 0.621%

references to legal or government documents and procedures

No Comments

No Known Activations