INDEX

Explanations

phrases related to positive affirmations and empowering statements

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

 Tours

-0.63

 resorts

-0.61

 Prior

-0.59

iency

-0.58

 Continental

-0.56

 Gaul

-0.56

 Lauder

-0.55

 Verge

-0.54

 Greenpeace

-0.54

 Rebell

-0.54

POSITIVE LOGITS

 gonna

0.99

ELF

0.96

pecially

0.88

been

0.86

selves

0.83

leeve

0.82

worth

0.79

lightly

0.77

 been

0.77

initely

0.75

Activations Density 0.435%

phrases related to positive affirmations and empowering statements

No Comments

No Known Activations