INDEX

Explanations

words with the suffix "-ing"

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

ãĥŀ

-0.67

å£

-0.62

 Columb

-0.60

ACP

-0.59

OHN

-0.58

ãĥ¤

-0.57

ãĥ

-0.56

veyard

-0.56

 COURT

-0.56

ESSION

-0.56

POSITIVE LOGITS

redients

1.27

tons

1.21

lass

1.17

roup

0.97

lasses

0.97

hetti

0.94

rab

0.89

hoff

0.89

ham

0.87

hai

0.86

Activations Density 0.031%

words with the suffix "-ing"

No Comments

No Known Activations