INDEX

Explanations

terms related to legal cases or criminal activities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ç¥ŀ

-1.17

Brexit

-0.81

 masc

-0.78

 haha

-0.77

Ïī

-0.76

iour

-0.75

âĻ

-0.75

pop

-0.74

Tomorrow

-0.74

ãĥİ

-0.74

POSITIVE LOGITS

 affidav

1.32

 redacted

1.32

 documents

1.20

Documents

1.20

 disclosures

1.18

 alleged

1.15

 Documents

1.14

 memos

1.12

 subpoen

1.12

 alleges

1.11

Activations Density 0.930%

terms related to legal cases or criminal activities

No Comments

No Known Activations