INDEX

Explanations

details related to specific organizations or institutions, particularly those promoting education and activism

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

nos

-0.69

eger

-0.67

Koh

-0.64

hig

-0.64

 Kinnikuman

-0.63

 Strauss

-0.63

ozyg

-0.62

ĸļ

-0.62

kr

-0.61

yi

-0.61

POSITIVE LOGITS

 affairs

0.62

 species

0.59

 succession

0.58

 armies

0.57

 menace

0.57

 regimes

0.57

 army

0.56

 Confederacy

0.55

 population

0.55

 oppress

0.55

Activations Density 0.099%

details related to specific organizations or institutions, particularly those promoting education and activism

No Comments

No Known Activations