INDEX

Explanations

references to research organizations or surveys

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

 Runner

-0.66

stood

-0.62

 dilig

-0.61

ynes

-0.61

 DRAG

-0.60

 suspensions

-0.60

 centrif

-0.60

 ultras

-0.60

Interstitial

-0.59

abilia

-0.58

POSITIVE LOGITS

aukee

1.15

Die

1.09

sburg

0.99

Pew

0.90

conn

0.90

die

0.89

sylvania

0.84

 Research

0.80

dor

0.79

ter

0.78

Activations Density 0.013%

references to research organizations or surveys

No Comments

No Known Activations