INDEX

Explanations

sentences related to politics and government

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

 Crescent

-0.37

 Sass

-0.35

 acronym

-0.35

 Auckland

-0.34

Zup

-0.34

 Invisible

-0.34

ãĤ¨ãĥ«

-0.34

surprisingly

-0.33

 bullish

-0.33

 USAF

-0.33

POSITIVE LOGITS

ÃĥÃĤ

0.48

=-=-

0.42

]=

0.42

-|

0.41

@#&

0.41

Â¯Â¯Â¯Â¯

0.41

WAYS

0.40

adem

0.40

*.

0.40

ornia

0.40

Activations Density 8.949%

sentences related to politics and government

No Comments

No Known Activations