INDEX

Explanations

quotations within quotation marks

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

Ļ½

-0.94

stant

-0.74

ĻĤ

-0.73

¾

-0.72

ãĥ´ãĤ¡

-0.68

¸

-0.67

¿

-0.65

paren

-0.64

ushi

-0.63

ãĥ¥

-0.63

POSITIVE LOGITS

/"

1.23

 moniker

0.70

 mentality

0.64

aneers

0.62

 mantra

0.62

 motto

0.61

 trademark

0.60

 remark

0.60

 designation

0.60

 appell

0.59

Activations Density 0.430%

quotations within quotation marks

No Comments

No Known Activations