INDEX

Explanations

words related to conflicts and disputes

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

CI

-0.67

âĹ¼

-0.63

 ILCS

-0.63

!.

-0.61

.;

-0.61

+.

-0.59

 whereas

-0.57

FTWARE

-0.55

$.

-0.54

dit

-0.53

POSITIVE LOGITS

 consisted

1.27

 consists

1.27

 lasted

1.21

is

1.16

 seemed

1.13

 arose

1.13

 appears

1.13

 revolves

1.10

was

1.10

 lasts

1.10

Activations Density 3.797%

words related to conflicts and disputes

No Comments

No Known Activations