INDEX

Explanations

phrases signaling the beginning of a new passage or section in text

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

 Archdemon

-0.61

arij

-0.60

natureconservancy

-0.59

 sshd

-0.58

 Breath

-0.56

 Strait

-0.56

ONSORED

-0.55

Edge

-0.54

mong

-0.54

iven

-0.53

POSITIVE LOGITS

tics

1.33

tical

1.32

abouts

1.26

tic

1.09

after

0.86

 Comes

0.84

with

0.81

adays

0.80

upon

0.79

ford

0.77

Activations Density 0.259%

phrases signaling the beginning of a new passage or section in text

No Comments

No Known Activations