INDEX

Explanations

mentions of legal or political terms related to regulations, human rights, and government 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Weston

-0.70

 Naples

-0.57

 Winc

-0.54

LH

-0.52

Kro

-0.52

ieri

-0.52

KS

-0.52

 reprinted

-0.51

NAS

-0.51

 Watkins

-0.51

POSITIVE LOGITS

1.43

"?

1.39

"—

1.39

%"

1.38

'?

1.32

"'

1.30

"-

1.30

[/

1.29

",

1.28

"!

1.28

Activations Density 4.696%

mentions of legal or political terms related to regulations, human rights, and government activities

No Comments

No Known Activations