INDEX

Explanations

terms and variations related to "communication."

oai_token-act-pair · gpt-4o-mini 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

olkien

-0.87

terday

-0.76

BALL

-0.76

Ole

-0.68

OPLE

-0.67

OHN

-0.65

IELD

-0.64

Downloadha

-0.64

DonaldTrump

-0.64

 Lank

-0.64

POSITIVE LOGITS

icator

1.55

icable

1.44

icative

1.41

icators

1.38

icating

1.21

icate

1.18

ique

1.16

iqu

1.12

icated

1.06

ciation

1.04

Activations Density 0.019%

terms and variations related to "communication."

No Comments

No Known Activations