INDEX

Explanations

Italian and Spanish words and names

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

etheless

-0.77

INGTON

-0.76

interrupted

-0.70

oola

-0.69

iaries

-0.69

orage

-0.67

hips

-0.67

ourcing

-0.64

otos

-0.64

abies

-0.64

POSITIVE LOGITS

lla

1.51

ller

1.42

llers

1.42

lli

1.39

lda

1.37

gger

1.31

zza

1.31

xt

1.31

lling

1.31

ppo

1.26

Activations Density 4.423%

Italian and Spanish words and names

No Comments

No Known Activations