INDEX

Explanations

words related to approval or disapproval of government actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Goth

-0.67

 Equality

-0.66

REDACTED

-0.66

 Immunity

-0.65

ISO

-0.65

FD

-0.63

[&

-0.62

imony

-0.59

 Danish

-0.59

 Nikon

-0.58

POSITIVE LOGITS

ving

1.76

ved

1.53

vable

1.49

ves

1.45

vers

1.43

ven

1.41

ptions

1.27

ption

1.26

pping

1.24

pling

1.22

Activations Density 0.044%

words related to approval or disapproval of government actions

No Comments

No Known Activations