INDEX

Explanations

pronouns such as "them" and "her," especially when referring to specific actions or objects

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

âĢ¢âĢ¢

-0.66

 Megan

-0.65

mire

-0.62

 Lori

-0.61

 Fulton

-0.60

 Salon

-0.60

CCC

-0.60

LH

-0.58

Jon

-0.58

 Laurie

-0.57

POSITIVE LOGITS

selves

1.75

atically

1.55

 selves

1.49

atic

1.42

self

1.42

alian

0.94

atics

0.94

 conduc

0.91

 individually

0.85

zbollah

0.83

Activations Density 0.526%

pronouns such as "them" and "her," especially when referring to specific actions or objects

No Comments

No Known Activations