INDEX

Explanations

historical events, specifically plots and plans related to political and military 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_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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĻĤ

-0.69

 manag

-0.68

 directions

-0.66

 unions

-0.66

axter

-0.66

 embodiments

-0.65

 skilled

-0.65

 parks

-0.64

 queen

-0.64

actionDate

-0.64

POSITIVE LOGITS

 Initiative

1.17

âĦ¢

1.13

 Consortium

1.13

 Project

1.11

 Collection

1.10

 Programme

1.09

 Facility

1.06

 Series

1.03

 Fund

1.02

 Committee

1.02

Activations Density 0.254%

historical events, specifically plots and plans related to political and military actions

No Comments

No Known Activations