INDEX

Explanations

information related to news articles and current events

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

username

-0.72

uds

-0.61

course

-0.60

cation

-0.59

orr

-0.58

 assum

-0.58

opter

-0.57

kat

-0.56

lished

-0.55

 Exhibition

-0.55

POSITIVE LOGITS

WASHINGTON

0.81

LIN

0.71

 COUNTY

0.71

POL

0.71

SHARE

0.70

 CITY

0.70

ccording

0.67

JUL

0.67

MEN

0.67

)--

0.65

Activations Density 1.675%

information related to news articles and current events

No Comments

No Known Activations