INDEX

Explanations

mentions of specific geographical locations or political entities

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

utherford

-0.85

lessly

-0.80

nels

-0.80

lot

-0.78

lier

-0.78

lished

-0.77

trap

-0.76

eus

-0.75

lest

-0.74

byss

-0.73

POSITIVE LOGITS

istani

0.95

 nationals

0.94

 government

0.92

 diplomats

0.88

 authorities

0.88

 embassies

0.87

 citizens

0.86

apolis

0.84

 Government

0.83

 Authorities

0.83

Activations Density 0.139%

mentions of specific geographical locations or political entities

No Comments

No Known Activations