INDEX

Explanations

phrases related to protests and demonstrations

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

å£«

-0.72

 Tycoon

-0.72

Reviewed

-0.71

amate

-0.71

nesota

-0.71

éĸ

-0.67

neau

-0.67

iciary

-0.65

itaire

-0.65

ATES

-0.64

POSITIVE LOGITS

 chanting

1.20

 chanted

1.12

 chants

1.10

 slogans

1.10

 chant

1.08

 louder

1.02

 aloud

0.95

 loudly

0.88

 sung

0.78

 chorus

0.77

Activations Density 0.023%

phrases related to protests and demonstrations

No Comments

No Known Activations