INDEX

Explanations

phrases related to personal interactions and conversations

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

iencies

-0.82

hesda

-0.76

massive

-0.70

ongevity

-0.70

agate

-0.69

 refurb

-0.69

romeda

-0.67

 dismantled

-0.67

 biodiversity

-0.67

SEA

-0.65

POSITIVE LOGITS

 aloud

1.64

 uttered

1.36

 speeches

1.33

 phrases

1.27

 louder

1.26

 loud

1.23

 slogans

1.22

 loudly

1.18

 poems

1.17

 plaint

1.15

Activations Density 3.260%

phrases related to personal interactions and conversations

No Comments

No Known Activations