INDEX

Explanations

phrases related to endings or conclusions

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

ub

-0.64

hee

-0.64

æ©Ł

-0.62

 acidic

-0.60

uni

-0.59

kaya

-0.58

available

-0.58

ickr

-0.57

 inherit

-0.57

pload

-0.56

POSITIVE LOGITS

owment

1.39

angering

1.34

ocrine

1.16

ocrin

1.09

angers

1.03

angered

1.00

game

0.99

orph

0.96

orses

0.95

eared

0.94

Activations Density 1.236%

phrases related to endings or conclusions

No Comments

No Known Activations