INDEX

Explanations

proper nouns related to various names or terms

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

IBLE

-0.75

ajor

-0.74

iture

-0.72

ually

-0.71

ational

-0.69

arians

-0.66

ional

-0.65

itarian

-0.65

 Examiner

-0.65

aciously

-0.64

POSITIVE LOGITS

mph

1.05

ramid

0.97

outube

0.96

akov

0.95

stal

0.92

nergy

0.92

ng

0.91

eah

0.90

mbol

0.90

metry

0.88

Activations Density 1.058%

proper nouns related to various names or terms

No Comments

No Known Activations