INDEX

Explanations

phrases related to personal experiences, opinions, and actions in various situations

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

selves

-0.87

 unison

-0.82

hub

-0.79

 respective

-0.69

 respectively

-0.63

merce

-0.58

 Authors

-0.58

 ourselves

-0.57

mination

-0.57

 Helpful

-0.57

POSITIVE LOGITS

 himself

1.77

 Himself

1.19

his

1.15

 herself

1.01

 charisma

0.80

 personally

0.80

 subordinates

0.79

 persona

0.76

 wife

0.76

His

0.74

Activations Density 4.563%

phrases related to personal experiences, opinions, and actions in various situations

No Comments

No Known Activations