INDEX

Explanations

statements about evaluation or reflection on a given situation or action

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

 tables

-0.65

 races

-0.64

 stripe

-0.64

 marg

-0.63

 fishes

-0.62

 Afgh

-0.61

 Grac

-0.61

lou

-0.60

LV

-0.59

 cuff

-0.58

POSITIVE LOGITS

 nevertheless

0.98

etheless

0.96

senal

0.95

 nonetheless

0.92

obyl

0.91

 likewise

0.90

¿½

0.90

also

0.86

Ĥİ

0.85

ŃĶ

0.80

Activations Density 1.725%

statements about evaluation or reflection on a given situation or action

No Comments

No Known Activations