INDEX

Explanations

references to time periods and historical 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_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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inki

-0.76

Fine

-0.72

aith

-0.65

cause

-0.63

because

-0.62

AB

-0.62

agra

-0.62

oops

-0.62

angu

-0.60

ãĥĩãĤ£

-0.60

POSITIVE LOGITS

we

0.82

 there

0.81

 meanwhile

0.74

 however

0.74

 thereafter

0.70

 moreover

0.69

idents

0.69

 successive

0.63

 studies

0.63

SPONSORED

0.61

Activations Density 0.134%

references to time periods and historical events

No Comments

No Known Activations