INDEX

Explanations

instructions or guidelines for a process of some kind

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

eri

-0.75

ainer

-0.72

efe

-0.64

._

-0.64

yne

-0.63

çīĪ

-0.62

hler

-0.62

iller

-0.61

?????-

-0.58

UTH

-0.58

POSITIVE LOGITS

 possible

1.22

 practicable

0.99

 Possible

0.76

 imaginable

0.69

 they

0.69

packages

0.67

 conceivable

0.67

 feas

0.66

daq

0.64

par

0.64

Activations Density 0.374%

instructions or guidelines for a process of some kind

No Comments

No Known Activations