INDEX

Explanations

names and titles related to individuals or characters

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

kefeller

-0.70

ruary

-0.69

 tire

-0.68

achine

-0.64

essor

-0.62

ORTS

-0.61

 tyre

-0.60

 orphans

-0.58

Reviewed

-0.57

 cigars

-0.56

POSITIVE LOGITS

idis

0.70

 Wonderland

0.70

vez

0.70

Pacific

0.68

umeric

0.67

è¦ļéĨĴ

0.67

iop

0.66

iris

0.65

=-=-=-=-=-=-=-=-

0.63

¥µ

0.63

Activations Density 0.180%

names and titles related to individuals or characters

No Comments

No Known Activations