INDEX

Explanations

information related to military training and operations

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

 leaks

-0.76

 pixels

-0.72

 headlights

-0.72

 Leviathan

-0.72

 eject

-0.71

bugs

-0.71

 frontman

-0.71

 seams

-0.71

 valves

-0.70

 leaking

-0.70

POSITIVE LOGITS

 curriculum

1.62

ploma

1.59

 vocational

1.51

 curric

1.50

 graduates

1.47

Students

1.45

 diploma

1.45

 tuition

1.43

graduate

1.42

 Teaching

1.41

Activations Density 0.602%

information related to military training and operations

No Comments

No Known Activations