INDEX

Explanations

locations or contexts within a narrative

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

apult

-0.79

rolet

-0.67

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.65

advertisement

-0.65

termin

-0.64

-0.63

ME

-0.62

mask

-0.61

Pwr

-0.61

yp

-0.61

POSITIVE LOGITS

upon

1.51

soever

1.36

abouts

0.99

 they

0.89

fore

0.87

ver

0.79

we

0.78

he

0.71

 users

0.70

she

0.69

Activations Density 1.185%

locations or contexts within a narrative

No Comments

No Known Activations