INDEX

Explanations

phrases related to laws, regulations, enforcement, and 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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

 Cros

-0.68

hiba

-0.67

 Tate

-0.66

 Events

-0.63

 Generations

-0.62

hematic

-0.62

Eco

-0.62

 Gree

-0.62

 Scion

-0.61

Os

-0.60

POSITIVE LOGITS

 enforcement

1.41

 Enforcement

1.17

enforcement

1.17

breakers

1.13

 abiding

1.11

 violations

1.10

 prohibiting

1.03

abiding

1.00

breaker

1.00

breaking

0.99

Activations Density 4.439%

phrases related to laws, regulations, enforcement, and criminal activities

No Comments

No Known Activations