INDEX

Explanations

references to significant events or milestones in various fields such as economics, transportation, sports, and politics

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

medium

-0.65

hun

-0.64

stall

-0.63

inders

-0.63

 Extras

-0.62

ãĥ¼ãĥ

-0.61

redients

-0.61

 juices

-0.61

 Bened

-0.61

 Eventually

-0.59

POSITIVE LOGITS

ever

1.14

 EVER

1.12

 ever

1.09

 consecutive

0.95

 since

0.89

 anniversary

0.84

 foray

0.78

Merit

0.75

clusively

0.75

 anywhere

0.73

Activations Density 2.576%

references to significant events or milestones in various fields such as economics, transportation, sports, and politics

No Comments

No Known Activations