INDEX

Explanations

phrases related to legislative or policy enforcement actions

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 appropri

-0.81

 spir

-0.75

 piping

-0.74

 inund

-0.74

 tackling

-0.74

 appreci

-0.72

 elev

-0.70

 bricks

-0.69

 accrued

-0.68

 invari

-0.68

POSITIVE LOGITS

âĢ¦)

1.42

...)

1.42

emphasis

1.29

*)

1.26

Laughs

1.23

?)

1.22

sic

1.17

hide

1.17

laughs

1.14

Courtesy

1.13

Activations Density 0.393%

phrases related to legislative or policy enforcement actions

No Comments

No Known Activations