INDEX

Explanations

phrases related to losing something or someone

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

sis

-0.69

INC

-0.63

INO

-0.63

rouse

-0.63

UP

-0.62

 solicitation

-0.62

ansky

-0.62

gon

-0.61

ATT

-0.60

 Aires

-0.60

POSITIVE LOGITS

 sight

0.91

 souls

0.87

 virginity

0.85

 aversion

0.84

 Souls

0.82

luster

0.81

 miser

0.80

 innocence

0.79

esville

0.78

 credibility

0.77

Activations Density 0.473%

phrases related to losing something or someone

No Comments

No Known Activations